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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    örü
    -0.07
     wand
    -0.07
    (parser
    -0.07
    .osgi
    -0.06
    mic
    -0.06
     Colleg
    -0.06
    Nature
    -0.06
    phone
    -0.06
    Arm
    -0.06
    /sys
    -0.06
    POSITIVE LOGITS
     Interfaces
    0.07
    .divide
    0.06
    ﻟ
    0.06
    klär
    0.06
     SelectList
    0.06
    _od
    0.06
     preco
    0.06
    985
    0.06
     Перед
    0.06
     depressing
    0.06
    Act Density 0.011%

    No Known Activations