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

    Neuronpedia

    INDEX
    Explanations

    display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _for
    -0.07
     deliberate
    -0.07
     tribute
    -0.06
     ними
    -0.06
     kali
    -0.06
     及
    -0.06
     Tatto
    -0.06
    explicit
    -0.06
    mary
    -0.06
    的地方
    -0.06
    POSITIVE LOGITS
    office
    0.07
     cardiovascular
    0.06
     parliamentary
    0.06
     dat
    0.06
    ्रद
    0.06
    FILENAME
    0.06
    _STATE
    0.06
    /block
    0.06
     Friendship
    0.06
     Foster
    0.06
    Act Density 0.011%

    No Known Activations