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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA National Helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ellum
    0.83
    ↵↵
    0.76
    S
    0.72
    ↵
    0.72
    Rh
    0.70
    授权
    0.64
    Span
    0.63
    spaced
    0.63
    <eos>
    0.63
    ส
    0.63
    POSITIVE LOGITS
    \.
    0.89
    :.
    0.79
    ;.
    0.77
     ListView
    0.77
     â
    0.75
     극
    0.75
     Transformer
    0.74
     Couldn
    0.74
     \|
    0.72
     ·
    0.72
    Act Density 0.005%

    No Known Activations