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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fn
    -0.06
    (Control
    -0.06
     BLUE
    -0.06
     revenge
    -0.06
    .setValue
    -0.06
     morally
    -0.06
    	build
    -0.06
    ï
    -0.06
     boarded
    -0.06
     been
    -0.06
    POSITIVE LOGITS
    ική
    0.08
     Sask
    0.07
    ロン
    0.06
     encontrar
    0.06
    \Controllers
    0.06
    .ex
    0.06
    九
    0.06
    ological
    0.06
     plusieurs
    0.06
    ा.
    0.06
    Act Density 0.065%

    No Known Activations