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

    Neuronpedia

    INDEX
    Explanations

    Auxiliary verbs and prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    请
    -0.07
    亚
    -0.06
    なの
    -0.06
    billing
    -0.06
    lops
    -0.06
    _matrices
    -0.06
     亚
    -0.06
    (post
    -0.06
    Cat
    -0.06
     Balt
    -0.06
    POSITIVE LOGITS
    	TokenNameIdentifier
    0.08
    apel
    0.07
     respectively
    0.07
    RED
    0.07
    ');");↵
    0.06
     Fellowship
    0.06
     pupils
    0.06
     pocit
    0.06
     حسب
    0.06
     resultat
    0.06
    Act Density 0.204%

    No Known Activations