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

    Neuronpedia

    INDEX
    Explanations

    structured data formats and elements related to tabular data representation

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

    tabular data with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.40
     CHAPITRE
    -0.40
    Toponymie
    -0.39
     ſche
    -0.38
     Baus
    -0.38
     "("
    -0.37
     ſer
    -0.36
     essentially
    -0.36
     juſ
    -0.35
     případ
    -0.35
    POSITIVE LOGITS
    :✨
    0.62
    UnusedPrivate
    0.61
     iprot
    0.57
     محفوظة
    0.56
     utafitiHapana
    0.53
    ThroughAttribute
    0.53
    CrossRef
    0.53
    stdc
    0.52
    
    0.52
     Chwiliwch
    0.51
    Act Density 0.064%

    No Known Activations