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

    Neuronpedia

    INDEX
    Explanations

    https://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    రుగులు
    0.42
    槭
    0.39
     ")";
    0.39
    Джек
    0.38
     \,.
    0.38
    ))=\
    0.37
    াফ
    0.37
     Uncertainty
    0.36
     architet
    0.36
    кономі
    0.35
    POSITIVE LOGITS
    !]
    1.03
    ],
    0.92
    ]
    0.87
    ];
    0.87
    ()]
    0.87
    ?]
    0.85
    ].
    0.84
    .]
    0.83
    ']
    0.83
    ,]
    0.80
    Act Density 0.114%

    No Known Activations