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

    Neuronpedia

    INDEX
    Explanations

    understand [topic]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lasting
    0.50
    marital
    0.44
    prob
    0.44
    put
    0.44
    B
    0.43
    reliable
    0.43
    Liên
    0.42
    O
    0.42
    times
    0.42
    競争
    0.42
    POSITIVE LOGITS
     enfermedades
    0.50
    ⎮
    0.47
     función
    0.46
     stockno
    0.46
     censure
    0.46
    DEBUGFS
    0.46
    இ
    0.46
     doenças
    0.45
     Geschichte
    0.44
     Tasmanian
    0.44
    Act Density 0.001%

    No Known Activations