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

    Neuronpedia

    INDEX
    Explanations

    amendment (legal, political)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peripheral
    -0.07
     Gross
    -0.07
    ldap
    -0.07
     gross
    -0.07
     heed
    -0.06
     hồi
    -0.06
    Else
    -0.06
     Jain
    -0.06
     spoke
    -0.06
    Sharp
    -0.06
    POSITIVE LOGITS
    ={↵
    0.07
     gdzie
    0.07
    =utf
    0.07
    lardır
    0.06
     эту
    0.06
    maktadır
    0.06
    klady
    0.06
     �
    0.06
    िं
    0.06
    addEventListener
    0.06
    Act Density 0.033%

    No Known Activations