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

    Neuronpedia

    INDEX
    Explanations

    alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $name
    -0.08
    	TR
    -0.07
     Za
    -0.07
    toHave
    -0.07
     Incre
    -0.07
     spectro
    -0.07
     sample
    -0.07
     otras
    -0.07
     Fon
    -0.07
    .getRandom
    -0.07
    POSITIVE LOGITS
     alignment
    0.10
    Aligned
    0.09
     align
    0.09
     aligned
    0.09
     ALIGN
    0.08
     Align
    0.08
     Alignment
    0.08
    RAIN
    0.08
    .align
    0.07
    -align
    0.07
    Act Density 0.012%

    No Known Activations