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

    Neuronpedia

    INDEX
    Explanations

    sexual assault hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    위를
    0.38
     recast
    0.36
     Mathis
    0.36
    পরিচিত
    0.36
    विधा
    0.35
     ({
    0.35
    बंधित
    0.34
     ($
    0.34
     Harper
    0.34
     mini
    0.33
    POSITIVE LOGITS
    boosting
    0.39
    তুন
    0.37
    十九章
    0.37
    hkse
    0.36
    ijnen
    0.36
     Mind
    0.36
    ImageBeforeText
    0.36
    ブラ
    0.36
     inaccuracy
    0.35
    Accessible
    0.35
    Act Density 0.016%

    No Known Activations