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

    Neuronpedia

    INDEX
    Explanations

    backslash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aprender
    -0.07
     Eisenhower
    -0.07
    かり
    -0.07
     claiming
    -0.07
     Gef
    -0.06
     bahçe
    -0.06
     favorable
    -0.06
    วางแผน
    -0.06
    -over
    -0.06
    义务教育
    -0.06
    POSITIVE LOGITS
     sane
    0.08
     muscles
    0.08
     domestic
    0.07
     enthusiasts
    0.07
    osphate
    0.07
    挑选
    0.07
     الحال
    0.06
     prominent
    0.06
     winners
    0.06
     intl
    0.06
    Act Density 0.007%

    No Known Activations