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

    Neuronpedia

    INDEX
    Explanations

    let's be honest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pounds
    0.79
     incompatibility
    0.73
     savior
    0.69
     ক্লা
    0.68
     pesan
    0.68
     kuin
    0.68
     message
    0.68
    dm
    0.68
    பம்
    0.67
     reversal
    0.66
    POSITIVE LOGITS
    )…
    0.82
     Organ
    0.73
    Internal
    0.72
    司法
    0.71
    ...");
    0.71
    ghed
    0.71
     уже
    0.70
    ..");
    0.69
    кр
    0.68
    Wend
    0.68
    Act Density 0.023%

    No Known Activations