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

    Neuronpedia

    INDEX
    Explanations

    steps, Engineer, vividly, coupon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    รู้สึก
    1.15
    ību
    1.12
     äuß
    1.10
    re
    1.09
    ímetros
    1.09
     dugo
    1.09
     Wahl
    1.08
    യം
    1.07
     poate
    1.07
    rust
    1.06
    POSITIVE LOGITS
    ति
    1.18
    ודה
    1.13
     confound
    1.13
    ])]
    1.09
    Delegate
    1.09
    कौन
    1.09
    aceous
    1.06
    ]").
    1.05
    neath
    1.05
    ्यू
    1.05
    Act Density 0.000%

    No Known Activations