Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    start of code blocks or the end of code lines/blocks

    oai_token-act-pair · gemini-2.0-flash

    special character sequences or programming functions

    np_token-act-pair-logits · gpt-4o-mini

    non-English code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UserScript
    -0.52
     AttributeSet
    -0.50
     חיצוניים
    -0.50
     StringField
    -0.44
     onCancelled
    -0.44
    absl
    -0.44
    halb
    -0.44
    Sucesor
    -0.43
     Glitch
    -0.43
    ốm
    -0.43
    POSITIVE LOGITS
    Espèce
    0.58
     Ouverture
    0.53
     Cataloging
    0.53
     CreateTagHelper
    0.51
    acker
    0.51
    anément
    0.51
    KURZBESCHREIBUNG
    0.49
    addCriterion
    0.49
     vermo
    0.49
     Maverick
    0.47
    Act Density 1.338%

    No Known Activations