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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Padding
    -0.07
     animate
    -0.07
     terre
    -0.06
     Silence
    -0.06
     พระ
    -0.06
    _values
    -0.06
    าระ
    -0.06
    -limit
    -0.06
     literal
    -0.06
    ";}
    -0.06
    POSITIVE LOGITS
     promot
    0.07
     cardi
    0.06
    arris
    0.06
    indsay
    0.06
    visualization
    0.06
     surviv
    0.06
    Jonathan
    0.06
    Justin
    0.06
     enthusi
    0.06
    dm
    0.06
    Act Density 0.035%

    No Known Activations