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

    Neuronpedia

    INDEX
    Explanations

    KO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Савезне
    -0.63
     betale
    -0.60
     CreateTagHelper
    -0.58
     EdgeInsets
    -0.58
     légitime
    -0.57
    InitVars
    -0.56
     wasnt
    -0.56
     houſe
    -0.56
     fhort
    -0.56
    ="'.$
    -0.55
    POSITIVE LOGITS
    .)
    1.00
    .),
    0.97
    .)}
    0.88
    ),
    0.87
    .);
    0.86
    ).
    0.85
    .).
    0.85
    );
    0.80
    .)-
    0.75
    ).-
    0.74
    Act Density 0.202%

    No Known Activations