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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FORWARD
    -0.08
     Though
    -0.07
    “If
    -0.07
     grapes
    -0.06
    ým
    -0.06
    摸
    -0.06
    "If
    -0.06
    DIM
    -0.06
     harbour
    -0.06
    "When
    -0.06
    POSITIVE LOGITS
    ']?></
    0.07
    usra
    0.07
    ")},↵
    0.07
     PdfPCell
    0.06
       ↵
    0.06
    　ﾊ
    0.06
    _processes
    0.06
    BracketAccess
    0.06
    =mysqli
    0.06
    rors
    0.06
    Act Density 0.020%

    No Known Activations