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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal protection and warranty disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    en banc or warrants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.74
     BoxFit
    -0.73
     ProtoMessage
    -0.73
     müſſen
    -0.71
    AddTagHelper
    -0.68
    <unused8>
    -0.67
    <unused43>
    -0.67
    <unused16>
    -0.66
    <unused14>
    -0.66
    <pad>
    -0.66
    POSITIVE LOGITS
    ,
    0.40
     EoL
    0.38
    en
    0.34
    EN
    0.32
    Obrázky
    0.32
     (
    0.31
    <bos>
    0.31
     In
    0.31
     al
    0.30
     en
    0.30
    Act Density 0.002%

    No Known Activations