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

    Neuronpedia

    INDEX
    Explanations

    convince and convey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    넛
    0.55
     Commencez
    0.51
    0.50
    랫
    0.49
     InputDecoration
    0.49
    వడం
    0.49
    渑
    0.47
    蜮
    0.47
     Instrument
    0.46
     Nouveau
    0.46
    POSITIVE LOGITS
    s
    0.55
    opilot
    0.54
    angka
    0.53
    id
    0.52
    ias
    0.52
    ón
    0.52
    è
    0.51
    yd
    0.50
    ed
    0.49
    ote
    0.49
    Act Density 0.000%

    No Known Activations