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

    Neuronpedia

    INDEX
    Explanations

    beneficial AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Porto
    -0.07
     into
    -0.07
    )+'
    -0.06
     آزمایش
    -0.06
     Cater
    -0.06
     Αγ
    -0.06
    _provider
    -0.06
    及其
    -0.06
    Processor
    -0.06
     Anyway
    -0.06
    POSITIVE LOGITS
     germ
    0.07
    AD
    0.07
    (abs
    0.06
     thải
    0.06
    ft
    0.06
     prosecuted
    0.06
     anniversary
    0.06
    IZ
    0.06
     olmadan
    0.06
    держ
    0.06
    Act Density 0.026%

    No Known Activations