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

    Neuronpedia

    INDEX
    Explanations

    (letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pistons
    -0.07
     ----------
    -0.06
     Edu
    -0.06
     Activ
    -0.06
     worst
    -0.06
     Blender
    -0.06
    449
    -0.06
    ND
    -0.06
    еб
    -0.06
    aging
    -0.06
    POSITIVE LOGITS
    )<=
    0.06
     धन
    0.06
     само
    0.06
    коном
    0.06
     edil
    0.06
    टन
    0.06
    JWT
    0.06
    (XML
    0.06
     محمود
    0.06
     bij
    0.06
    Act Density 0.009%

    No Known Activations