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

    Neuronpedia

    INDEX
    Explanations

    mac words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tooltip
    0.93
    ributive
    0.86
     exs
    0.86
     গোলা
    0.84
     Absch
    0.83
    犹豫
    0.82
     sessionStorage
    0.81
    чені
    0.81
     Adequate
    0.80
     quello
    0.80
    POSITIVE LOGITS
    intosh
    1.24
    artney
    1.05
    regor
    0.98
    adamia
    0.93
    tım
    0.90
    Pherson
    0.87
    rae
    0.87
    enzie
    0.83
     OSX
    0.83
    uffin
    0.83
    Act Density 0.062%

    No Known Activations