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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    438
    -0.08
    ector
    -0.06
    ических
    -0.06
    екту
    -0.06
     películ
    -0.06
     державної
    -0.06
    akah
    -0.06
    ecut
    -0.06
    .handleClick
    -0.06
    324
    -0.06
    POSITIVE LOGITS
     mobil
    0.08
     연구
    0.07
     merg
    0.07
    istorical
    0.07
    (any
    0.06
    ่างก
    0.06
     ="
    0.06
     rnd
    0.06
    _null
    0.06
    knowledge
    0.06
    Act Density 0.035%

    No Known Activations