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

    Neuronpedia

    INDEX
    Explanations

    CGI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slut
    -0.07
     Fakült
    -0.07
     tomb
    -0.06
     pus
    -0.06
    ЛА
    -0.06
     masks
    -0.06
     disastr
    -0.06
    _RANK
    -0.06
    -la
    -0.06
     入
    -0.06
    POSITIVE LOGITS
     CG
    0.12
     CGI
    0.12
    cgi
    0.11
    .cgi
    0.11
    CG
    0.11
     cgi
    0.09
    _cg
    0.09
    iggs
    0.08
    (CG
    0.08
     cg
    0.08
    Act Density 0.004%

    No Known Activations