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

    Neuronpedia

    INDEX
    Explanations

    prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tablet
    -0.07
     янва
    -0.07
    .perform
    -0.06
    quiv
    -0.06
     extracts
    -0.06
    (args
    -0.06
    处
    -0.06
     которые
    -0.06
     Presence
    -0.06
     cafes
    -0.06
    POSITIVE LOGITS
    NU
    0.07
    ож
    0.06
    	nil
    0.06
    /public
    0.06
     허
    0.06
    sport
    0.06
    .ef
    0.06
     Hunters
    0.06
    wizard
    0.06
    nox
    0.06
    Act Density 0.228%

    No Known Activations