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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     עולה
    -0.07
     Flores
    -0.07
    쟤
    -0.07
    而导致
    -0.06
    'im
    -0.06
     Euro
    -0.06
     Reg
    -0.06
    켬
    -0.06
     precaution
    -0.06
    充满
    -0.06
    POSITIVE LOGITS
     раств
    0.07
    棉
    0.07
     Clinic
    0.07
    ấp
    0.07
    Attempts
    0.07
    电线
    0.07
     guideline
    0.06
    inent
    0.06
    他们的
    0.06
    一樣
    0.06
    Act Density 0.099%

    No Known Activations