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

    Neuronpedia

    INDEX
    Explanations

    is known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tero
    0.44
     groupes
    0.40
    苦
    0.39
    cue
    0.38
    Erro
    0.38
     groupe
    0.38
     گروه
    0.38
    榻
    0.37
    ࿔
    0.37
    𒅆
    0.36
    POSITIVE LOGITS
     CON
    0.42
     high
    0.41
    সম্যান
    0.40
     DHL
    0.40
     Supreme
    0.40
     garbage
    0.40
     IOC
    0.40
    UCI
    0.39
     Voj
    0.39
     मदर
    0.39
    Act Density 0.000%

    No Known Activations