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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psz
    -0.07
    =user
    -0.06
    owel
    -0.06
    Miami
    -0.06
    Liverpool
    -0.06
    Digit
    -0.06
     AAP
    -0.06
    Jordan
    -0.06
    (score
    -0.06
     Mish
    -0.06
    POSITIVE LOGITS
     pozor
    0.07
     Machinery
    0.07
    /memory
    0.07
     peně
    0.06
     planetary
    0.06
     Co
    0.06
     nepř
    0.06
     windowHeight
    0.06
    @Slf
    0.06
     crossing
    0.06
    Act Density 0.003%

    No Known Activations