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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Metal
    -0.08
     Pan
    -0.07
     cams
    -0.07
    ere
    -0.07
     Porter
    -0.07
     cam
    -0.06
     Fast
    -0.06
     Steph
    -0.06
    ERE
    -0.06
     Panthers
    -0.06
    POSITIVE LOGITS
    ैं.↵
    0.07
     yo
    0.07
    
    0.07
    ！↵↵
    0.07
    ":{↵
    0.06
     маль
    0.06
    ;!
    0.06
    .mode
    0.06
    альне
    0.06
    ональ
    0.06
    Act Density 0.051%

    No Known Activations