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

    Neuronpedia

    INDEX
    Explanations

    ){

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    face
    -0.07
    edge
    -0.07
    .Seek
    -0.07
    hb
    -0.06
    út
    -0.06
     cloak
    -0.06
    =options
    -0.06
    but
    -0.06
    亸
    -0.06
     thế
    -0.06
    POSITIVE LOGITS
    茧
    0.08
    OTP
    0.07
     imprisonment
    0.07
     Until
    0.07
    iams
    0.07
    堂
    0.07
    愚
    0.07
     fishermen
    0.07
    .compat
    0.07
    弘扬
    0.07
    Act Density 0.000%

    No Known Activations