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

    Neuronpedia

    INDEX
    Explanations

    functioning states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hull
    0.78
    pele
    0.74
     প্রশাসনিক
    0.73
    ieros
    0.72
     поступа
    0.69
     hull
    0.69
     сбор
    0.69
    oxyl
    0.69
    outputText
    0.69
    outline
    0.67
    POSITIVE LOGITS
     activated
    1.35
     activation
    1.34
     aktiviert
    1.29
    Activation
    1.27
     functioning
    1.22
     vervangen
    1.15
     Activation
    1.15
    Activated
    1.13
     활
    1.07
     hoạt
    1.07
    Act Density 0.318%

    No Known Activations