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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OID
    -0.07
    -W
    -0.06
     Bashar
    -0.06
     dhe
    -0.06
    -b
    -0.06
    _h
    -0.06
    inner
    -0.06
     Clintons
    -0.06
    +N
    -0.06
    _dur
    -0.06
    POSITIVE LOGITS
    ;
↵
↵
↵
↵
    0.06
    역
    0.06
    .nome
    0.06
     créd
    0.06
     поки
    0.06
     شهرد
    0.06
     학
    0.06
    itive
    0.06
    Carrier
    0.06
     sóc
    0.06
    Act Density 0.058%

    No Known Activations