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

    Neuronpedia

    INDEX
    Explanations

    programming and software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gło
    -0.07
    /delete
    -0.07
    -detail
    -0.07
     Slug
    -0.07
     Indians
    -0.06
    膦
    -0.06
    屬
    -0.06
    (branch
    -0.06
    Constraint
    -0.06
    Ann
    -0.06
    POSITIVE LOGITS
    bies
    0.07
    icy
    0.07
     ebp
    0.07
     imprisoned
    0.07
     Hicks
    0.07
     Pack
    0.07
     acceptable
    0.06
     przy
    0.06
    azy
    0.06
    -row
    0.06
    Act Density 0.023%

    No Known Activations