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

    Neuronpedia

    INDEX
    Explanations

    problems, discomfort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burning
    -1.13
     Burning
    -1.07
    Burning
    -0.92
    burning
    -0.89
    GraphicsUnit
    -0.77
    esModule
    -0.71
     roulant
    -0.71
     pintadas
    -0.69
     burned
    -0.67
     supérieurs
    -0.66
    POSITIVE LOGITS
    work
    0.63
    stalt
    0.56
    en
    0.56
    ly
    0.56
    es
    0.54
    works
    0.52
    dos
    0.51
    room
    0.50
    ro
    0.49
    ely
    0.49
    Act Density 0.136%

    No Known Activations