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

    Neuronpedia

    INDEX
    Explanations

    understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dev
    -0.07
    看望
    -0.07
     poking
    -0.07
    鳐
    -0.06
     teamed
    -0.06
     compassion
    -0.06
    AutoresizingMaskIntoConstraints
    -0.06
    	com
    -0.06
    �
    -0.06
    /disc
    -0.06
    POSITIVE LOGITS
    氣
    0.07
     #$
    0.06
    Ἦ
    0.06
    Stretch
    0.06
    𝗨
    0.06
    _R
    0.06
    utivo
    0.06
     calculates
    0.06
     vrouw
    0.06
     derive
    0.06
    Act Density 0.004%

    No Known Activations