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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allein
    -0.08
     sostiene
    -0.07
     диагноз
    -0.07
     interfering
    -0.07
     a
    -0.07
    -0.07
     alene
    -0.07
     tensors
    -0.07
    astar
    -0.07
     Frag
    -0.07
    POSITIVE LOGITS
    ಿಗ್ಗ
    0.10
    _iteration
    0.09
     jika
    0.09
    ighth
    0.09
    _iterations
    0.08
     inning
    0.08
    ಗ್ಗೆ
    0.08
    Rounds
    0.08
    _batches
    0.08
     musim
    0.08
    Act Density 0.010%
    No Known Activations