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

    Neuronpedia

    INDEX
    Explanations

    a sequence of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Allowed
    0.52
    KINS
    0.48
    ANEOUS
    0.47
    COOH
    0.46
     typos
    0.46
     бясплат
    0.44
    Scha
    0.44
     cellulosic
    0.44
     फडण
    0.44
    ন্যায়
    0.43
    POSITIVE LOGITS
    até
    0.47
    cd
    0.45
     regarder
    0.43
     signaling
    0.42
     Encounter
    0.40
    ocation
    0.39
     migration
    0.39
    <tbody>
    0.39
    تمر
    0.38
     encounter
    0.38
    Act Density 0.006%

    No Known Activations