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

    Neuronpedia

    INDEX
    Explanations

    television

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [B
    -0.07
     ctx
    -0.07
    -shared
    -0.07
     UTIL
    -0.07
     Roh
    -0.07
    ctors
    -0.07
    振り
    -0.07
    投机
    -0.07
     Earl
    -0.07
     Jo
    -0.07
    POSITIVE LOGITS
     defamation
    0.08
    airport
    0.07
    (validate
    0.07
     devuelve
    0.07
    حضار
    0.07
    أل
    0.07
     validar
    0.07
    YPRE
    0.07
     brasile
    0.07
     VAR
    0.07
    Act Density 0.024%

    No Known Activations