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

    Neuronpedia

    INDEX
    Explanations

    TV shows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dojo
    -0.07
    原因
    -0.06
     Suche
    -0.06
     شما
    -0.06
     wires
    -0.06
     schemes
    -0.06
     unanswered
    -0.06
    位置
    -0.06
     několika
    -0.05
    _rank
    -0.05
    POSITIVE LOGITS
    -An
    0.07
    erç
    0.06
     вим
    0.06
    閉
    0.06
    rial
    0.06
     osc
    0.06
    φο
    0.06
    (mod
    0.06
     overturn
    0.06
    _CELL
    0.06
    Act Density 0.000%

    No Known Activations