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

    Neuronpedia

    INDEX
    Explanations

    Grammatical sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ма
    -0.06
    alam
    -0.06
    988
    -0.06
    /per
    -0.06
    )index
    -0.06
    /O
    -0.06
    /o
    -0.06
    ainment
    -0.06
    beta
    -0.06
    umps
    -0.06
    POSITIVE LOGITS
     Inches
    0.07
    ModelState
    0.07
     grunt
    0.07
     Herman
    0.06
     Sammy
    0.06
     wrongful
    0.06
    ——
    0.06
    —which
    0.06
     payday
    0.06
    Howard
    0.06
    Act Density 0.238%

    No Known Activations