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

    Neuronpedia

    INDEX
    Explanations

    verification status

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PLEMENT
    0.53
    脹
    0.48
    EG
    0.46
     EG
    0.46
    𝗛
    0.46
     HC
    0.44
    mole
    0.44
    胀
    0.44
    ELO
    0.44
    عند
    0.43
    POSITIVE LOGITS
    ifies
    0.59
     bud
    0.52
     defra
    0.51
     want
    0.50
    ified
    0.50
     defraud
    0.50
    verifica
    0.50
     express
    0.49
     lik
    0.49
     heard
    0.49
    Act Density 0.000%

    No Known Activations