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

    Neuronpedia

    INDEX
    Explanations

    foreign language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vols
    0.51
     الايه
    0.48
     Regul
    0.48
     Darren
    0.48
    бль
    0.47
     Dar
    0.46
     Deut
    0.45
     blau
    0.45
     těch
    0.45
     Rend
    0.45
    POSITIVE LOGITS
    rovers
    0.44
    inato
    0.44
    貨
    0.44
    簿
    0.42
    itano
    0.42
     möjligt
    0.41
    RIP
    0.41
    え
    0.41
    uation
    0.40
    ithmetic
    0.40
    Act Density 0.005%

    No Known Activations