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

    Neuronpedia

    INDEX
    Explanations

    minute (BPM)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificent
    0.52
     தெரிவி
    0.51
    inairement
    0.49
     affirme
    0.49
    ially
    0.49
     telah
    0.48
    ariamente
    0.48
     בפ
    0.46
     recebeu
    0.46
     joins
    0.46
    POSITIVE LOGITS
    ป
    0.46
    Му
    0.45
    newL
    0.44
    ኵ
    0.44
     undesired
    0.43
    사람
    0.43
    Romantic
    0.43
     حرام
    0.42
    items
    0.42
    Modulo
    0.42
    Act Density 0.000%

    No Known Activations