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

    Neuronpedia

    INDEX
    Explanations

    flask app object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nessy
    1.03
     تی
    0.99
    trt
    0.96
    nY
    0.95
     Tucker
    0.94
    Tucker
    0.92
     youths
    0.91
    tur
    0.91
     Tayler
    0.91
     surveillance
    0.90
    POSITIVE LOGITS
     Cos
    0.83
     COSM
    0.80
     Maud
    0.80
    CO
    0.77
     ete
    0.76
     KO
    0.75
     Malk
    0.75
     Knock
    0.75
    EP
    0.75
     Mich
    0.73
    Act Density 0.847%

    No Known Activations