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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theme
    -0.07
    Anchor
    -0.07
    unc
    -0.07
     الشمس
    -0.07
     Code
    -0.07
     الخيار
    -0.07
     beide
    -0.07
    ugu
    -0.07
    	parameters
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .L
    0.07
     GR
    0.07
     должна
    0.07
    ;br
    0.07
    GLOSS
    0.06
    appendTo
    0.06
     lineman
    0.06
    ставил
    0.06
    销量
    0.06
     מאפשר
    0.06
    Act Density 0.319%

    No Known Activations