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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _behavior
    -0.07
     plywood
    -0.06
     очередь
    -0.06
     slopes
    -0.06
     utiliza
    -0.06
    ovní
    -0.06
     Beverly
    -0.06
     Prot
    -0.06
    .power
    -0.06
     Loy
    -0.06
    POSITIVE LOGITS
    prevState
    0.07
    (delta
    0.06
    229
    0.06
    ิว
    0.06
     bana
    0.06
    yard
    0.06
     ''){↵
    0.06
    	dest
    0.06
    ίδ
    0.06
    	exp
    0.05
    Act Density 0.013%

    No Known Activations