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

    Neuronpedia

    INDEX
    Explanations

    code/system output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .NUM
    -0.07
    MH
    -0.07
    험
    -0.06
     takdir
    -0.06
    nid
    -0.06
    __',
    -0.06
     definitely
    -0.06
    Wir
    -0.06
    ンパ
    -0.06
    PAT
    -0.06
    POSITIVE LOGITS
     قال
    0.07
     التج
    0.07
    �始化
    0.06
     migrate
    0.06
     fileList
    0.06
    ResultSet
    0.06
     Cassandra
    0.06
    izza
    0.06
     Parker
    0.06
    ↵ ↵
    0.06
    Act Density 0.000%

    No Known Activations