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

    Neuronpedia

    INDEX
    Explanations

    display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lawyers
    -0.07
    olecules
    -0.07
     meditation
    -0.06
     Cemetery
    -0.06
     Henry
    -0.06
     revolver
    -0.06
     vess
    -0.06
     geometry
    -0.06
     McCoy
    -0.06
    _Metadata
    -0.06
    POSITIVE LOGITS
    .inflate
    0.07
    كه
    0.06
    �
    0.06
    gf
    0.06
    >)
    0.06
     praž
    0.06
    ]
    0.06
     lashes
    0.06
    美
    0.06
    Autom
    0.06
    Act Density 0.043%

    No Known Activations