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

    Neuronpedia

    INDEX
    Explanations

    business performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忤
    -0.07
     bufio
    -0.07
    桹
    -0.07
     admired
    -0.07
     Mozart
    -0.07
     Ethiopia
    -0.07
    (isinstance
    -0.07
    𝗺
    -0.07
    trzymać
    -0.07
    gradation
    -0.07
    POSITIVE LOGITS
    	url
    0.08
    onaut
    0.07
    	word
    0.07
    Plan
    0.07
    阵容
    0.07
    READ
    0.07
    	write
    0.07
     Start
    0.06
    	Json
    0.06
    .chat
    0.06
    Act Density 0.012%

    No Known Activations