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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apolis
    -0.07
     Pist
    -0.06
    Validator
    -0.06
    생활
    -0.06
    ัค
    -0.06
     пенс
    -0.05
     Voc
    -0.05
    swick
    -0.05
    InstanceOf
    -0.05
    _<?
    -0.05
    POSITIVE LOGITS
     integrates
    0.07
    thern
    0.07
    iên
    0.07
     prayer
    0.06
    .gpu
    0.06
    atemala
    0.06
     Autonomous
    0.06
    ziehung
    0.06
    inheritDoc
    0.06
     Romero
    0.06
    Act Density 0.010%

    No Known Activations