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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fame
    -0.07
    _scripts
    -0.07
     Previous
    -0.07
    .each
    -0.07
     WD
    -0.07
    -scalable
    -0.07
     nest
    -0.06
     ejemplo
    -0.06
     (*.
    -0.06
    -da
    -0.06
    POSITIVE LOGITS
    _dialog
    0.07
     verification
    0.07
     undergraduate
    0.06
    TH
    0.06
    This
    0.06
    Human
    0.06
    这款
    0.06
    产生的
    0.06
     AV
    0.06
    妳
    0.06
    Act Density 0.141%

    No Known Activations