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

    Neuronpedia

    INDEX
    Explanations

    psychology and human behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nouns
    -0.07
     das
    -0.07
    .dm
    -0.07
     Counsel
    -0.07
     columna
    -0.07
     Sugar
    -0.07
    feito
    -0.07
    (pol
    -0.06
     Für
    -0.06
    一般来说
    -0.06
    POSITIVE LOGITS
    ęki
    0.07
     geleceği
    0.07
    增值
    0.07
    移植
    0.07
    +E
    0.07
    	H
    0.07
    ripple
    0.07
     đáo
    0.07
    奘
    0.06
    瑧
    0.06
    Act Density 0.149%

    No Known Activations