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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ichten
    -0.07
     tỷ
    -0.07
    iren
    -0.07
    ağını
    -0.07
    offs
    -0.07
     milhões
    -0.07
    izzling
    -0.07
    ificación
    -0.07
     definitive
    -0.06
     million
    -0.06
    POSITIVE LOGITS
    -txt
    0.07
    .lu
    0.07
     blogger
    0.07
    ás
    0.07
    _bi
    0.06
     walk
    0.06
     Iterator
    0.06
    פעם
    0.06
    centroid
    0.06
    '>
    0.06
    Act Density 0.125%

    No Known Activations