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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comedy
    -0.06
     가족
    -0.06
     EOF
    -0.06
    种
    -0.06
     cylinders
    -0.06
    対
    -0.06
    .scope
    -0.06
     ignorance
    -0.06
     Labs
    -0.06
    mPid
    -0.06
    POSITIVE LOGITS
    metic
    0.06
    inst
    0.06
    має
    0.06
    船
    0.06
    เธอ
    0.06
     Klein
    0.06
    波
    0.06
    했던
    0.06
     placeholder
    0.06
    nock
    0.06
    Act Density 0.027%

    No Known Activations