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

    Neuronpedia

    INDEX
    Explanations

    ointed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Patt
    -0.07
    _COST
    -0.07
     Roulette
    -0.07
    _DATABASE
    -0.06
    .currentUser
    -0.06
    _HOT
    -0.06
    model
    -0.06
     deceptive
    -0.06
    .modelo
    -0.06
     adultos
    -0.06
    POSITIVE LOGITS
    #error
    0.07
    τηκε
    0.07
    datum
    0.06
     Thời
    0.06
    #\
    0.06
     nejd
    0.06
     Arguments
    0.06
    ез
    0.06
     TEAM
    0.06
     nay
    0.06
    Act Density 0.000%

    No Known Activations