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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remedy
    -0.07
    .Login
    -0.07
     resolution
    -0.07
     Pain
    -0.07
     camera
    -0.07
     Administrative
    -0.07
     Velvet
    -0.07
     sign
    -0.07
     dissertation
    -0.07
     bran
    -0.07
    POSITIVE LOGITS
    ��
    0.07
     UIGraphics
    0.06
    :'',
    0.06
    هور
    0.06
    skému
    0.06
    학년
    0.06
    .argv
    0.06
    それは
    0.06
    장을
    0.06
     DATABASE
    0.06
    Act Density 0.307%

    No Known Activations