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

    Neuronpedia

    INDEX
    Explanations

    Neural network architectures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tuesday
    -0.07
     Ya
    -0.07
    Spread
    -0.07
    енную
    -0.06
     Saturday
    -0.06
    ac
    -0.06
     slightly
    -0.06
    ao
    -0.06
     criteria
    -0.06
     Eagle
    -0.06
    POSITIVE LOGITS
    GetObject
    0.07
     getpid
    0.06
    ([...
    0.06
    _don
    0.06
     Chess
    0.06
    います
    0.06
     Assass
    0.06
     перш
    0.06
    _QUESTION
    0.06
    _icall
    0.06
    Act Density 0.058%

    No Known Activations