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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     таких
    -0.07
     яких
    -0.07
    �
    -0.07
     worsh
    -0.06
    bringing
    -0.06
    雅
    -0.06
    lyn
    -0.06
    .POS
    -0.06
    _pars
    -0.06
    qd
    -0.06
    POSITIVE LOGITS
     modulation
    0.06
     dissip
    0.06
    .amazon
    0.06
     توان
    0.06
     del
    0.06
     validations
    0.05
    ulling
    0.05
    ORMAL
    0.05
    ическая
    0.05
    (parse
    0.05
    Act Density 0.026%

    No Known Activations