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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _utilities
    -0.06
     TIMESTAMP
    -0.06
    828
    -0.06
    Blend
    -0.06
    .EndsWith
    -0.06
    Assertions
    -0.06
    sched
    -0.06
    390
    -0.06
    원의
    -0.06
     Novel
    -0.06
    POSITIVE LOGITS
     frau
    0.07
     статті
    0.07
     기타
    0.06
    Also
    0.06
     busiest
    0.06
     січ
    0.06
    0.06
    robat
    0.06
    declare
    0.06
    этому
    0.06
    Act Density 0.815%

    No Known Activations