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

    Neuronpedia

    INDEX
    Explanations

    conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictatorship
    -0.06
    ็นผ
    -0.06
     hizmeti
    -0.06
    atory
    -0.06
    ğa
    -0.06
     ears
    -0.06
     frameworks
    -0.06
    fortawesome
    -0.06
    :';↵
    -0.06
     نزد
    -0.06
    POSITIVE LOGITS
    -packages
    0.07
     fullfile
    0.07
     identifying
    0.07
     blames
    0.06
    <-
    0.06
     cout
    0.06
     hinges
    0.06
     соот
    0.06
     ویژ
    0.06
    (candidate
    0.06
    Act Density 0.073%

    No Known Activations