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

    Neuronpedia

    INDEX
    Explanations

    afraid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Context
    -0.08
    _SUPPORT
    -0.06
     Zem
    -0.06
     З
    -0.06
     ấy
    -0.06
     Carr
    -0.06
     Rounded
    -0.06
     dispon
    -0.06
    _context
    -0.06
     За
    -0.06
    POSITIVE LOGITS
     afraid
    0.09
    ........................
    0.08
    gradation
    0.07
    .money
    0.07
    149
    0.06
    razier
    0.06
     \\↵
    0.06
    157
    0.06
    aving
    0.06
    ................................
    0.06
    Act Density 0.006%

    No Known Activations