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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orting
    -0.07
     Fakültesi
    -0.06
     record
    -0.06
     Pep
    -0.06
    	wait
    -0.06
    aul
    -0.06
     disciple
    -0.06
    Routine
    -0.06
     highs
    -0.06
    etal
    -0.06
    POSITIVE LOGITS
     ช
    0.07
     oportun
    0.06
     nét
    0.06
     criticised
    0.06
    行动
    0.06
    			
↵
    0.06
     mistr
    0.06
     hardship
    0.06
    ф
    0.06
    Usuario
    0.06
    Act Density 0.006%

    No Known Activations