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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stanley
    -0.07
     schemes
    -0.06
     Fran
    -0.06
    shed
    -0.06
     Sterling
    -0.06
    .jd
    -0.06
     Philips
    -0.06
    یر
    -0.06
    爵
    -0.06
    ADR
    -0.06
    POSITIVE LOGITS
     σει
    0.06
    De
    0.06
     teaspoons
    0.06
     CF
    0.06
     advancement
    0.06
     θε
    0.06
     бес
    0.06
     purported
    0.06
    de
    0.06
    него
    0.06
    Act Density 0.000%

    No Known Activations