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

    Neuronpedia

    INDEX
    Explanations

    pointing or handing something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offence
    -0.07
     oversee
    -0.06
            
↵
↵
    -0.06
     lands
    -0.06
     leicht
    -0.06
    $type
    -0.06
    -data
    -0.06
    Converted
    -0.06
     Paz
    -0.06
     famed
    -0.06
    POSITIVE LOGITS
    .slides
    0.07
    Во
    0.06
    =?";↵
    0.06
     نمودار
    0.06
     princip
    0.06
    ungalow
    0.06
    대표
    0.06
     resisting
    0.06
    �
    0.06
    HO
    0.06
    Act Density 0.114%

    No Known Activations