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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Antique
    -0.07
     emp
    -0.07
     ταιν
    -0.07
    ,No
    -0.06
     subplot
    -0.06
    Pok
    -0.06
    _acc
    -0.06
    .Str
    -0.06
    bmp
    -0.06
    iset
    -0.06
    POSITIVE LOGITS
    concept
    0.06
    -bearing
    0.06
    :id
    0.06
    SPACE
    0.06
     backlash
    0.06
     newcomers
    0.06
     Newly
    0.06
    enos
    0.06
     léč
    0.06
    常
    0.06
    Act Density 0.012%

    No Known Activations