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

    Neuronpedia

    INDEX
    Explanations

    Attractors, current state, powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ခံ
    0.50
    恚
    0.47
     է
    0.47
    MVC
    0.46
    akum
    0.46
     काटने
    0.44
     tummy
    0.44
    寰
    0.44
    สู
    0.43
    透
    0.43
    POSITIVE LOGITS
     forment
    0.48
     Tripoli
    0.47
     comme
    0.47
    غراف
    0.46
    னர்
    0.46
     mercado
    0.46
     presid
    0.46
    на
    0.46
     remained
    0.46
     regiones
    0.46
    Act Density 0.000%

    No Known Activations