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

    Neuronpedia

    INDEX
    Explanations

    square bracketed phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    URLs and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .«
    0.45
    ).—
    0.45
    ’).
    0.42
    )。
    0.42
    。《
    0.42
    »).
    0.41
    )<\
    0.41
    рики
    0.41
     afsl
    0.40
     %).
    0.40
    POSITIVE LOGITS
    ?]
    1.51
    !]
    1.48
    +]
    1.48
     ]
    1.38
    ...]
    1.23
    ,]
    1.21
    .]
    1.20
     ]:
    1.15
     ],
    1.13
    ][
    1.11
    Act Density 0.026%

    No Known Activations