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
    िप
    -0.07
    _activities
    -0.06
     vitae
    -0.06
    ura
    -0.06
    (tuple
    -0.06
    Directory
    -0.06
    aret
    -0.06
    crit
    -0.06
     attribute
    -0.06
    虫
    -0.06
    POSITIVE LOGITS
     olmam
    0.07
    .cal
    0.07
     خط
    0.06
    umbotron
    0.06
    queued
    0.06
     كام
    0.06
     Гер
    0.06
     Anglic
    0.06
     UCLA
    0.06
     expos
    0.06
    Act Density 0.003%

    No Known Activations