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

    Neuronpedia

    INDEX
    Explanations

    hyperbolas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sett
    -0.08
    -0.08
    uale
    -0.08
    alne
    -0.08
     aired
    -0.08
     Feeling
    -0.07
    ingss
    -0.07
    �
    -0.07
    até
    -0.07
     Outs
    -0.07
    POSITIVE LOGITS
    _radius
    0.10
    Radius
    0.09
     radius
    0.09
    (radius
    0.08
    ADIUS
    0.08
    /root
    0.08
    radius
    0.08
    0.08
    _root
    0.08
     horizon
    0.08
    Act Density 0.020%
    No Known Activations