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

    Neuronpedia

    INDEX
    Explanations

    errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orce
    -0.07
     Reed
    -0.06
    -'.$
    -0.06
     ending
    -0.06
    rush
    -0.06
     Tone
    -0.06
     Falling
    -0.06
    ULATOR
    -0.06
    Advertising
    -0.06
     aliases
    -0.06
    POSITIVE LOGITS
    ,name
    0.07
    lld
    0.07
     overlooking
    0.06
    (properties
    0.06
     [-
    0.06
     вона
    0.06
     فضای
    0.06
    .multipart
    0.06
    稍
    0.06
     _
    0.06
    Act Density 0.064%

    No Known Activations