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

    Neuronpedia

    INDEX
    Explanations

    code, configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     existential
    -0.07
     toxins
    -0.07
    Easy
    -0.07
    stage
    -0.07
    ﴀ
    -0.06
     prime
    -0.06
    Ga
    -0.06
     Scandinavian
    -0.06
    之所以
    -0.06
     Spa
    -0.06
    POSITIVE LOGITS
    _KEYWORD
    0.09
    빕
    0.08
    ทด
    0.07
    чрежден
    0.07
    .threshold
    0.07
    orrow
    0.07
     втор
    0.07
    삣
    0.07
     borrow
    0.07
    ᤖ
    0.07
    Act Density 0.044%

    No Known Activations