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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Creating
    -0.07
     �
    -0.07
     decorations
    -0.07
    unsqueeze
    -0.07
     Lawyers
    -0.07
     Rated
    -0.07
    ной
    -0.07
    asbourg
    -0.06
     Salisbury
    -0.06
     sĩ
    -0.06
    POSITIVE LOGITS
     OMG
    0.06
     tonight
    0.06
    (Main
    0.06
    :first
    0.06
    İK
    0.06
     fd
    0.06
    俄
    0.06
     rc
    0.06
     연락
    0.06
    (Module
    0.06
    Act Density 0.000%

    No Known Activations