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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saf
    -0.06
    印
    -0.06
    *b
    -0.06
    'D
    -0.06
    скор
    -0.06
    _easy
    -0.06
    Nach
    -0.06
    `,↵
    -0.06
    됨
    -0.06
    zung
    -0.06
    POSITIVE LOGITS
    .trailingAnchor
    0.07
    ers
    0.06
    .property
    0.06
    assword
    0.06
    .onClick
    0.06
     Science
    0.06
     يوليو
    0.06
     Poss
    0.06
     SMALL
    0.06
     stakeholders
    0.06
    Act Density 0.008%

    No Known Activations