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

    Neuronpedia

    INDEX
    Explanations

    generate.resourcest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inadequ
    0.38
     correcto
    0.38
     impos
    0.37
     isValid
    0.37
    وقع
    0.36
    𓇼
    0.36
     vacated
    0.35
     ObjectMapper
    0.35
    ⇔
    0.35
    keyDown
    0.35
    POSITIVE LOGITS
     טי
    0.40
     ев
    0.39
    .".,
    0.38
     tornado
    0.36
     ז
    0.36
    ân
    0.35
    Further
    0.35
     Based
    0.35
     Turbulence
    0.35
    煥
    0.35
    Act Density 0.003%

    No Known Activations