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

    Neuronpedia

    INDEX
    Explanations

    skills and abilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тран
    -0.07
     Robot
    -0.06
     interactions
    -0.06
     neob
    -0.06
     Epid
    -0.06
     Sob
    -0.06
     Church
    -0.06
     knives
    -0.06
    .gridx
    -0.06
    	height
    -0.05
    POSITIVE LOGITS
     yür
    0.07
    _warning
    0.07
    QA
    0.07
     диви
    0.07
     функци
    0.07
     골
    0.06
    shuffle
    0.06
     mell
    0.06
    -play
    0.06
     εκεί
    0.06
    Act Density 0.123%

    No Known Activations