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

    Neuronpedia

    INDEX
    Explanations

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    als
    -0.27
    ally
    -0.26
    ä¼ļéķ¿
    -0.25
    çī§åľº
    -0.25
    å¼Ĥåľ°
    -0.25
    umer
    -0.25
    åı¯èĥ½åĩºçİ°
    -0.24
    å¥
    -0.24
    ])/
    -0.24
     мало
    -0.23
    POSITIVE LOGITS
    ileged
    0.30
    ICES
    0.30
     deflect
    0.27
    pyx
    0.26
     freel
    0.26
    Synopsis
    0.25
     theirs
    0.25
    ÐIJÐŀ
    0.25
    pees
    0.25
    .selector
    0.24
    Act Density 0.042%

    No Known Activations