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

    Neuronpedia

    INDEX
    Explanations

    First-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chuckled
    -0.07
    -dependent
    -0.07
     материал
    -0.07
     hospital
    -0.07
     assertEquals
    -0.07
     simulated
    -0.07
    ーリ
    -0.06
    -wheel
    -0.06
     ambulance
    -0.06
    finished
    -0.06
    POSITIVE LOGITS
    ledik
    0.07
     Libertarian
    0.06
    igr
    0.06
     seh
    0.06
    ίτ
    0.06
    zept
    0.06
    .renderer
    0.06
    .goods
    0.06
     OnDestroy
    0.06
    αρίου
    0.06
    Act Density 0.026%

    No Known Activations