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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Charging
    -0.07
     yardımcı
    -0.07
     ortaya
    -0.06
    Artifact
    -0.06
    faith
    -0.06
     Hubb
    -0.06
     Potter
    -0.06
     charging
    -0.06
    시
    -0.06
     setData
    -0.06
    POSITIVE LOGITS
     SCH
    0.06
    sson
    0.06
    _migration
    0.06
     currentTime
    0.06
    ugh
    0.06
    acher
    0.06
    *.
    0.06
    alties
    0.06
    ElapsedTime
    0.06
     coop
    0.06
    Act Density 0.026%

    No Known Activations