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

    Neuronpedia

    INDEX
    Explanations

    scarleteen.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immediacy
    0.73
    picklist
    0.70
     अवलंब
    0.70
     cip
    0.69
    ঔ
    0.68
     cioc
    0.67
    চূ
    0.65
    ՛
    0.65
    披
    0.65
    reading
    0.64
    POSITIVE LOGITS
    ams
    0.66
    }^{+
    0.63
    Ko
    0.62
    សា
    0.62
    ámenes
    0.62
     coul
    0.60
    bor
    0.60
     Burgh
    0.59
     Consol
    0.59
     Colleg
    0.59
    Act Density 0.007%

    No Known Activations