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

    Neuronpedia

    INDEX
    Explanations

    ass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pv
    -0.08
     Flynn
    -0.07
     рівня
    -0.07
    ani
    -0.07
     rule
    -0.07
    oro
    -0.07
    upp
    -0.06
    ////////////////////////////////////////////////////////////////
    -0.06
     consider
    -0.06
     mov
    -0.06
    POSITIVE LOGITS
    574
    0.07
    _MISS
    0.07
     Service
    0.06
     địch
    0.06
    امج
    0.06
    τσ
    0.06
     grac
    0.06
    Ath
    0.06
    вают
    0.06
    케
    0.06
    Act Density 0.000%

    No Known Activations