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

    Neuronpedia

    INDEX
    Explanations

    item

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    black
    -0.07
     distint
    -0.07
    当然
    -0.07
    '])
    -0.07
    mu
    -0.07
    _IMPL
    -0.07
    _cipher
    -0.07
    .PERMISSION
    -0.07
     श
    -0.06
    ській
    -0.06
    POSITIVE LOGITS
    >:
    0.06
    directive
    0.06
    MES
    0.06
    _)↵
    0.06
     rune
    0.06
        
    0.06
     Elves
    0.06
     Happ
    0.05
     BACK
    0.05
     COOKIE
    0.05
    Act Density 0.000%

    No Known Activations