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

    Neuronpedia

    INDEX
    Explanations

    management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bounding
    -0.07
     knowledge
    -0.06
     dolls
    -0.06
     home
    -0.06
     repo
    -0.06
    William
    -0.06
    -based
    -0.06
    cean
    -0.06
     radial
    -0.06
     privat
    -0.06
    POSITIVE LOGITS
    增
    0.07
    �
    0.07
    оді
    0.07
     condol
    0.06
    adní
    0.06
     از
    0.06
     chiefs
    0.06
     baseman
    0.06
     TAG
    0.06
    .raises
    0.06
    Act Density 0.061%

    No Known Activations