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

    Neuronpedia

    INDEX
    Explanations

    Source and destination addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Debian
    -0.07
    [iVar
    -0.07
    >{@
    -0.07
    Checkpoint
    -0.06
    珍
    -0.06
    uate
    -0.06
     perpetr
    -0.06
     يوم
    -0.06
    列
    -0.06
    .hasMore
    -0.06
    POSITIVE LOGITS
     STD
    0.07
     Beef
    0.07
     aids
    0.06
     Assault
    0.06
     lantern
    0.06
    estination
    0.06
     dbl
    0.06
     sprink
    0.06
     Early
    0.06
     Karma
    0.06
    Act Density 0.005%

    No Known Activations