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

    Neuronpedia

    INDEX
    Explanations

    networks and design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spiral
    -0.07
    215
    -0.07
    Disable
    -0.07
    holder
    -0.07
     load
    -0.06
    ;";↵
    -0.06
    *z
    -0.06
    *pow
    -0.06
     edit
    -0.06
    _density
    -0.06
    POSITIVE LOGITS
     gö
    0.06
     MOD
    0.06
    .Std
    0.06
     organising
    0.06
    :NSUTF
    0.06
    ayette
    0.06
     spor
    0.06
     گذ
    0.06
     hurl
    0.05
    -op
    0.05
    Act Density 0.254%

    No Known Activations