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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kids
    -0.07
    亜
    -0.07
    zimmer
    -0.07
     realms
    -0.06
     дис
    -0.06
    	case
    -0.06
    Dim
    -0.06
     anomaly
    -0.06
     Rename
    -0.06
    박
    -0.06
    POSITIVE LOGITS
    ійської
    0.06
     comb
    0.06
    -exc
    0.06
    gems
    0.06
     prem
    0.06
     αυτή
    0.06
    /token
    0.06
    がい
    0.06
    :nth
    0.05
     premi
    0.05
    Act Density 0.000%

    No Known Activations