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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     будут
    -0.07
    antas
    -0.06
     stopwatch
    -0.06
     Alonso
    -0.06
    .readFileSync
    -0.06
     supp
    -0.06
     guild
    -0.06
     Lucia
    -0.06
     Torch
    -0.06
    IW
    -0.05
    POSITIVE LOGITS
    Particles
    0.07
     kre
    0.06
    Company
    0.06
    ภาษ
    0.06
    <K
    0.06
    ��제
    0.06
    announcement
    0.06
     Tribute
    0.06
    [method
    0.06
     STDMETHOD
    0.06
    Act Density 0.050%

    No Known Activations