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

    Neuronpedia

    INDEX
    Explanations

    comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
      
    -0.07
    _eta
    -0.07
    .cont
    -0.06
     ####
    -0.06
    anja
    -0.06
    gam
    -0.06
    rejected
    -0.06
    KP
    -0.06
    KF
    -0.06
    ”的
    -0.06
    POSITIVE LOGITS
     CommonModule
    0.07
    .sql
    0.07
     vitro
    0.07
    _RIGHT
    0.07
     فصل
    0.06
    ["@
    0.06
     Lib
    0.06
     util
    0.06
    ан
    0.06
    (Class
    0.06
    Act Density 0.011%

    No Known Activations