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

    Neuronpedia

    INDEX
    Explanations

    cause/appears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    秵
    0.55
    ಿದ್ದೇವೆ
    0.54
    Ⲥ
    0.50
    ാമ
    0.50
     entretien
    0.50
    䁂
    0.50
    ടതി
    0.49
    点で
    0.49
     azonban
    0.48
     clarifications
    0.48
    POSITIVE LOGITS
    io
    0.59
    X
    0.57
    LL
    0.56
    Dimension
    0.54
    um
    0.53
    OC
    0.52
     get
    0.52
    _
    0.50
    JavaScript
    0.50
    ile
    0.50
    Act Density 0.000%

    No Known Activations