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

    Neuronpedia

    INDEX
    Explanations

    technical/instructional text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ायत
    -0.07
    łą
    -0.06
    jak
    -0.06
    ‏
    -0.06
    免费
    -0.06
     varios
    -0.06
     تحميل
    -0.06
     meal
    -0.06
     เกม
    -0.06
    ्ब
    -0.06
    POSITIVE LOGITS
     naming
    0.07
    	TRACE
    0.07
     ^{°}
    0.06
     �
    0.06
     Naming
    0.06
    라피
    0.06
     Sandy
    0.06
     speaking
    0.06
     evacuate
    0.06
    Logger
    0.06
    Act Density 0.000%

    No Known Activations