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

    Neuronpedia

    INDEX
    Explanations

    greetings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descriptions
    -0.08
     psychiatrist
    -0.07
    jad
    -0.07
    elts
    -0.07
    caption
    -0.07
    Albert
    -0.07
    irement
    -0.06
     конт
    -0.06
    Completion
    -0.06
    inary
    -0.06
    POSITIVE LOGITS
    [keys
    0.06
    %"),↵
    0.06
    ]';↵
    0.06
     neu
    0.06
    method
    0.06
    IColor
    0.05
     ça
    0.05
    .Geometry
    0.05
    حل
    0.05
    (docs
    0.05
    Act Density 0.069%

    No Known Activations