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

    Neuronpedia

    INDEX
    Explanations

    code blocks and control structures

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     h
    -0.62
     H
    -0.58
     New
    -0.57
     Good
    -0.57
     
    -0.56
     R
    -0.56
     Mor
    -0.55
     a
    -0.54
     r
    -0.54
     "
    -0.53
    POSITIVE LOGITS
     pinulongan
    0.86
     myſelf
    0.84
     itſelf
    0.80
     <=",
    0.79
     يتيمه
    0.77
     becauſe
    0.75
     мәкал
    0.74
    Datuak
    0.73
     дописавши
    0.73
     ddelweddau
    0.72
    Act Density 0.194%

    No Known Activations