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

    Neuronpedia

    INDEX
    Explanations

    text about toys and construction sets

    oai_token-act-pair · gemini-2.0-flash

    imagination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.51
    نگار
    -0.49
    degenerate
    -0.48
    MATCH
    -0.47
    วง
    -0.47
    אי
    -0.46
    ">{{$
    -0.46
    ฎ
    -0.46
    جویان
    -0.46
     Match
    -0.43
    POSITIVE LOGITS
     tartalomajánló
    0.73
    RectangleBorder
    0.67
    Kids
    0.63
     Childhood
    0.63
     contextLoads
    0.62
     beginnetje
    0.60
     childhood
    0.59
     kids
    0.58
     Kids
    0.57
    行政区划
    0.57
    Act Density 0.885%

    No Known Activations