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

    Neuronpedia

    INDEX
    Explanations

    ier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    091
    -0.07
    CONF
    -0.07
    /format
    -0.07
    Ord
    -0.06
     Regression
    -0.06
     relax
    -0.06
     CONTACT
    -0.06
    Divider
    -0.06
     chip
    -0.06
    จะ
    -0.06
    POSITIVE LOGITS
     dřev
    0.07
    .defaultValue
    0.07
    .entrySet
    0.07
    專
    0.07
     yn
    0.06
    をつ
    0.06
    spotify
    0.06
     compassionate
    0.06
    .TYPE
    0.06
    bedo
    0.06
    Act Density 0.003%

    No Known Activations