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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    になります
    -0.07
     VAR
    -0.07
     pedigree
    -0.07
    荨
    -0.07
    🇹
    -0.07
     lawsuit
    -0.07
    哥伦
    -0.07
    .ix
    -0.07
    gląd
    -0.07
    (codec
    -0.07
    POSITIVE LOGITS
    EventType
    0.07
     alphabet
    0.07
     Twelve
    0.07
     то
    0.07
     selects
    0.07
    ::*
    0.07
    0.07
     sizes
    0.07
     schools
    0.07
    \\/
    0.07
    Act Density 0.068%

    No Known Activations