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

    Neuronpedia

    INDEX
    Explanations

    Accessibility and availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     várias
    0.43
     dogged
    0.42
    脨
    0.42
     सर्वा
    0.41
     आले
    0.40
    ramento
    0.40
     ออก
    0.40
    <b>
    0.40
    cat
    0.39
    arsi
    0.39
    POSITIVE LOGITS
    Vote
    0.50
     Voters
    0.48
    \%)
    0.47
    AVOA
    0.47
    INUS
    0.46
    IW
    0.46
    NEEDED
    0.46
    fton
    0.46
    ᅦ
    0.45
    Triple
    0.45
    Act Density 0.001%

    No Known Activations