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

    Neuronpedia

    INDEX
    Explanations

    choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ориг
    -0.07
    kân
    -0.06
    imulation
    -0.06
     Sentinel
    -0.06
     timers
    -0.06
     Mapping
    -0.06
     WN
    -0.06
    xDF
    -0.06
     císa
    -0.06
    _BUF
    -0.06
    POSITIVE LOGITS
    }">↵
    0.06
     ginger
    0.06
    ")]↵↵
    0.06
    ër
    0.06
    .Cookie
    0.06
    preserve
    0.06
     autistic
    0.06
     know
    0.06
    uch
    0.06
    232
    0.06
    Act Density 0.000%

    No Known Activations