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

    Neuronpedia

    INDEX
    Explanations

    say characters limit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    是个
    -0.07
     disagreement
    -0.07
     Harmony
    -0.07
    ipients
    -0.07
     Turning
    -0.06
    EMY
    -0.06
    Raised
    -0.06
     detailed
    -0.06
     notably
    -0.06
     Js
    -0.06
    POSITIVE LOGITS
    pecies
    0.07
     autocomplete
    0.07
    	ext
    0.07
    λεύ
    0.06
    /~
    0.06
    -containing
    0.06
    msp
    0.06
     frequ
    0.06
     piş
    0.06
    xCD
    0.06
    Act Density 0.061%

    No Known Activations