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

    Neuronpedia

    INDEX
    Explanations

    computational fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یت
    1.06
    س
    1.05
    ोन
    0.99
    یک
    0.89
    رو
    0.85
    માં
    0.81
    сро
    0.81
    changers
    0.81
     کنکریاں
    0.80
    sld
    0.79
    POSITIVE LOGITS
    '
    1.48
    )
    1.25
    ]
    1.23
    _
    1.10
    >
    1.01
    }
    1.00
    ↵
    0.99
     be
    0.96
    ↵↵
    0.95
    ?
    0.90
    Act Density 0.005%

    No Known Activations