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

    Neuronpedia

    INDEX
    Explanations

    acquisition and appraisal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.47
     timer
    0.44
    زة
    0.44
     grips
    0.44
     control
    0.42
     manage
    0.42
    פל
    0.41
     niveau
    0.41
    िवर्स
    0.41
    getSource
    0.40
    POSITIVE LOGITS
    ième
    0.57
    idential
    0.52
     curviliné
    0.51
    ête
    0.50
     Nhân
    0.47
    สำหรับการ
    0.46
    तेला
    0.46
    மாக
    0.46
     lézards
    0.46
     พิจิก
    0.46
    Act Density 0.002%

    No Known Activations