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

    Neuronpedia

    INDEX
    Explanations

    gut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tenant
    -0.07
    SC
    -0.07
    atasets
    -0.07
     świata
    -0.07
     §
    -0.07
    ﺵ
    -0.07
    verture
    -0.07
    屦
    -0.07
    ataset
    -0.07
     dataset
    -0.07
    POSITIVE LOGITS
     ButterKnife
    0.07
    (math
    0.07
    调侃
    0.07
    �
    0.07
     timed
    0.07
     geen
    0.07
    	cf
    0.07
     dik
    0.07
    题主
    0.07
     Acid
    0.06
    Act Density 0.007%

    No Known Activations