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

    Neuronpedia

    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OV
    -0.07
     retailer
    -0.06
    Wonder
    -0.06
    MEMORY
    -0.06
    Storm
    -0.06
    гар
    -0.06
    Buf
    -0.06
    steller
    -0.06
    coll
    -0.06
    rail
    -0.06
    POSITIVE LOGITS
     Tutor
    0.07
    }↵
    0.07
    '}↵
    0.07
     incarcerated
    0.07
     داخلی
    0.07
    suma
    0.07
    >'.↵
    0.07
    }]↵
    0.07
    ibilit
    0.06
    )}}"
    0.06
    Act Density 0.000%

    No Known Activations