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

    Neuronpedia

    INDEX
    Explanations

    mathematical/scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .easy
    -0.07
    	break
    -0.07
    ց
    -0.07
    泇
    -0.07
    耰
    -0.06
    ÜN
    -0.06
     spokesperson
    -0.06
    �
    -0.06
    �
    -0.06
     thinly
    -0.06
    POSITIVE LOGITS
     Pur
    0.08
    惯
    0.07
     assaulted
    0.07
     intents
    0.06
    gro
    0.06
    /modules
    0.06
    ENTION
    0.06
     besides
    0.06
     đánh
    0.06
    怪物
    0.06
    Act Density 0.063%

    No Known Activations