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

    Neuronpedia

    INDEX
    Explanations

    instances of prepositions and auxiliary verbs along with words indicating significance and conflict

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gación
    -0.56
     stop
    -0.53
     Stop
    -0.52
     defeat
    -0.51
    ilever
    -0.49
     avoid
    -0.47
    uesas
    -0.47
     ign
    -0.47
    labelledby
    -0.47
    躇
    -0.47
    POSITIVE LOGITS
     count
    0.82
     שוליים
    0.76
    WithIOException
    0.71
    SourceChecksum
    0.70
     Infórmanos
    0.70
    count
    0.67
     Count
    0.65
    SharedDtor
    0.61
    municipi
    0.60
    قایناقلار
    0.58
    Act Density 4.243%

    No Known Activations