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

    Neuronpedia

    INDEX
    Explanations

    separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iking
    -0.08
    993
    -0.07
    .Mod
    -0.06
     κο
    -0.06
    .Settings
    -0.06
    \modules
    -0.06
    ΟΙ
    -0.06
    作用
    -0.06
    leground
    -0.06
    (com
    -0.06
    POSITIVE LOGITS
     Separ
    0.09
     separating
    0.09
     separ
    0.09
     separated
    0.08
     separate
    0.08
    ximity
    0.08
     separation
    0.07
     segregation
    0.07
     Shepard
    0.07
    Separator
    0.07
    Act Density 0.022%

    No Known Activations