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

    Neuronpedia

    INDEX
    Explanations

    64

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stejně
    -0.06
     sắp
    -0.06
    �
    -0.06
     nights
    -0.06
    IOD
    -0.06
    addOn
    -0.05
     gerekli
    -0.05
    $html
    -0.05
    _ASSIGN
    -0.05
    Sibling
    -0.05
    POSITIVE LOGITS
    64
    0.08
    Charsets
    0.07
    _modifier
    0.07
     manipulating
    0.07
     Tall
    0.07
    Introduced
    0.06
    일본
    0.06
     Accountability
    0.06
    .temp
    0.06
     LEGO
    0.06
    Act Density 0.003%

    No Known Activations