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

    Neuronpedia

    INDEX
    Explanations

    Measurement units and values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    5
    -0.07
    amac
    -0.07
    оры
    -0.06
    riages
    -0.06
     Scotch
    -0.06
    24
    -0.06
    哲
    -0.06
     hisset
    -0.06
    4
    -0.06
    ımızın
    -0.06
    POSITIVE LOGITS
     кис
    0.08
     radiation
    0.07
     cracking
    0.06
    processed
    0.06
    ิน
    0.06
     venture
    0.06
    .fn
    0.06
    token
    0.06
     shy
    0.06
     moveTo
    0.06
    Act Density 0.041%

    No Known Activations