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

    Neuronpedia

    INDEX
    Explanations

    research verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loop
    -0.07
    logs
    -0.07
    charset
    -0.07
     outputFile
    -0.06
     次
    -0.06
    Code
    -0.06
     Code
    -0.06
    796
    -0.06
     blatantly
    -0.06
     Legs
    -0.06
    POSITIVE LOGITS
     aktiv
    0.07
     choisir
    0.06
    .pivot
    0.06
    ‌دهد
    0.06
    ▋
    0.06
    (coeffs
    0.06
    bounce
    0.06
    imm
    0.06
    almö
    0.06
    //****************************************************************************
    0.06
    Act Density 0.060%

    No Known Activations