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

    Neuronpedia

    INDEX
    Explanations

    cc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     їм
    -0.07
    favor
    -0.07
    outlined
    -0.07
    POS
    -0.06
    @param
    -0.06
    -desc
    -0.06
     Orlando
    -0.06
    mere
    -0.06
     �
    -0.06
     Shib
    -0.06
    POSITIVE LOGITS
     OU
    0.07
    '}),↵
    0.06
    oque
    0.06
    ISMATCH
    0.06
     ModelRenderer
    0.06
     RTL
    0.06
     ping
    0.06
    _between
    0.06
     constit
    0.06
     конструкции
    0.06
    Act Density 0.001%

    No Known Activations