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

    Neuronpedia

    INDEX
    Explanations

    Comparisons / Descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μμα
    -0.07
    startsWith
    -0.07
    郭
    -0.06
    _before
    -0.06
     Definition
    -0.06
    namespace
    -0.06
    endsWith
    -0.06
    _Show
    -0.06
    らの
    -0.06
     MAK
    -0.06
    POSITIVE LOGITS
     costumes
    0.08
    ernetes
    0.06
     generics
    0.06
    国際
    0.06
    ειο
    0.06
     번째
    0.06
     cared
    0.06
     agricult
    0.06
    imeo
    0.06
     sidl
    0.06
    Act Density 0.258%

    No Known Activations