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

    Neuronpedia

    INDEX
    Explanations

    deleting data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zilla
    -0.07
     darling
    -0.07
     mega
    -0.06
     рекоменда
    -0.06
     PNG
    -0.06
     harmless
    -0.06
    元
    -0.06
     Against
    -0.06
    insert
    -0.06
    	swap
    -0.06
    POSITIVE LOGITS
    lum
    0.06
     =>{↵
    0.06
    DIFF
    0.06
     الذه
    0.06
     ดาว
    0.06
     aque
    0.06
    ikt
    0.06
    će
    0.06
     irres
    0.06
    Associ
    0.06
    Act Density 0.022%

    No Known Activations