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

    Neuronpedia

    INDEX
    Explanations

    -image

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pund
    -0.07
    kům
    -0.06
     alphabetical
    -0.06
    �
    -0.06
     xbox
    -0.06
    lle
    -0.06
    LOSS
    -0.06
     Yup
    -0.06
    .solution
    -0.06
    /module
    -0.06
    POSITIVE LOGITS
     dissip
    0.07
     Colombian
    0.07
     caric
    0.07
     QtAws
    0.07
    thr
    0.07
    енное
    0.07
     textured
    0.07
    zip
    0.06
     Latter
    0.06
     replicas
    0.06
    Act Density 0.002%

    No Known Activations