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

    Neuronpedia

    INDEX
    Explanations

    reverse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ={}
    -0.08
     എന്നും
    -0.08
     vertically
    -0.08
     enem
    -0.08
    trap
    -0.08
     afọ
    -0.07
    	en
    -0.07
     irony
    -0.07
     {};
↵
    -0.07
    ഡിയ
    -0.07
    POSITIVE LOGITS
    .sep
    0.07
     palp
    0.07
     corresponds
    0.07
     correspond
    0.07
    Sounds
    0.07
     अलग
    0.07
     collect
    0.07
    .collect
    0.07
     corresponde
    0.07
    рыв
    0.07
    Act Density 0.002%

    No Known Activations