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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gradient
    -0.07
    ollower
    -0.07
    บาท
    -0.06
     clever
    -0.06
     Cbd
    -0.06
    maid
    -0.06
     sehr
    -0.06
     motif
    -0.06
    ега
    -0.06
     Chef
    -0.06
    POSITIVE LOGITS
    0.06
    _ref
    0.06
    0.06
    .native
    0.06
     mitig
    0.06
    όμε
    0.06
    ropolitan
    0.06
    0.06
    AMERA
    0.06
    imagin
    0.06
    Act Density 0.003%

    No Known Activations