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

    Neuronpedia

    INDEX
    Explanations

    validity or proof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Imaging
    0.50
    EntityFramework
    0.46
    躊
    0.45
     मातर
    0.45
     decision
    0.45
    체의
    0.44
     curricula
    0.43
    CONFLICT
    0.43
    >>::
    0.42
    袮
    0.42
    POSITIVE LOGITS
     तुम्ही
    0.47
    питы
    0.47
     elong
    0.46
    laughs
    0.46
    lerine
    0.46
    ível
    0.45
     Airborne
    0.45
     comunes
    0.44
    lidir
    0.44
     éve
    0.44
    Act Density 0.000%

    No Known Activations