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

    Neuronpedia

    INDEX
    Explanations

    auxillary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =username
    -0.06
     되어
    -0.06
    stick
    -0.06
    ทางการ
    -0.06
    liche
    -0.06
    userData
    -0.06
    NotBlank
    -0.06
     تمام
    -0.06
     знать
    -0.06
    670
    -0.06
    POSITIVE LOGITS
     randomized
    0.07
     )
    0.07
    ollapsed
    0.06
     ψ
    0.06
    ')↵↵↵
    0.06
    cerpt
    0.06
    ercises
    0.06
     extraction
    0.06
    uib
    0.06
    NS
    0.06
    Act Density 0.207%

    No Known Activations