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

    Neuronpedia

    INDEX
    Explanations

    technical configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ord
    -0.06
     cả
    -0.06
    ess
    -0.06
     Brexit
    -0.06
    oard
    -0.06
    γγραφ
    -0.06
     beauty
    -0.06
     image
    -0.06
    ocal
    -0.06
     Shield
    -0.06
    POSITIVE LOGITS
    (example
    0.07
    .fecha
    0.07
    (startTime
    0.07
     خداوند
    0.07
    連
    0.06
    (question
    0.06
     DFA
    0.06
    θι
    0.06
     vary
    0.06
    Parm
    0.06
    Act Density 0.001%

    No Known Activations