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

    Neuronpedia

    INDEX
    Explanations

    through...trouble...battery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     השני
    0.50
    на
    0.47
     lunghezza
    0.47
     ära
    0.47
    手機
    0.47
     frutta
    0.46
     ветра
    0.46
     krás
    0.45
     Han
    0.45
     gió
    0.45
    POSITIVE LOGITS
    init
    0.45
    _
    0.41
    checker
    0.41
    Init
    0.38
    Posted
    0.38
     விடு
    0.38
    edil
    0.38
    checkout
    0.37
    шед
    0.37
    cedor
    0.37
    Act Density 0.000%

    No Known Activations