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

    Neuronpedia

    INDEX
    Explanations

    icolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BOSE
    -0.07
     Sexo
    -0.07
     Carter
    -0.07
    UInteger
    -0.07
    uzzy
    -0.06
    Sector
    -0.06
    ніше
    -0.06
    атку
    -0.06
    レビ
    -0.06
     Seahawks
    -0.06
    POSITIVE LOGITS
     ($_
    0.07
     admitting
    0.06
    ",$
    0.06
     refusing
    0.06
    	host
    0.06
    oggles
    0.06
     Scre
    0.06
    forum
    0.06
     IRQ
    0.06
    (end
    0.06
    Act Density 0.000%

    No Known Activations