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

    Neuronpedia

    INDEX
    Explanations

    Hugging Face, Torch, transformers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    1.19
    ва
    1.15
    ENCE
    1.13
    ри
    1.05
    া
    1.03
    ić
    1.02
     intérieure
    1.02
    де
    1.01
    マリン
    0.98
    ר
    0.98
    POSITIVE LOGITS
    should
    0.98
    s
    0.97
    ssss
    0.92
     desenvolver
    0.89
    sans
    0.88
    skins
    0.86
    shaders
    0.86
    rdquo
    0.85
    ]})
    0.84
    sion
    0.84
    Act Density 0.188%

    No Known Activations