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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /User
    -0.07
     jes
    -0.06
     心
    -0.06
    ่วง
    -0.06
    eec
    -0.06
    cps
    -0.06
    まで
    -0.06
     misunderstanding
    -0.06
    нулся
    -0.06
     sans
    -0.06
    POSITIVE LOGITS
    965
    0.08
    _TREE
    0.07
    شهر
    0.07
     appropri
    0.06
    score
    0.06
    lookup
    0.06
    porto
    0.06
     chamber
    0.06
    лава
    0.06
     Graf
    0.06
    Act Density 0.020%

    No Known Activations