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

    Neuronpedia

    INDEX
    Explanations

    what should

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raz
    0.52
     Bahan
    0.49
    thus
    0.48
     Madre
    0.47
    dash
    0.46
    ri
    0.45
    et
    0.45
    די
    0.45
    ρι
    0.44
    ches
    0.44
    POSITIVE LOGITS
     core
    0.54
    ",
    0.52
    .",
    0.49
    ]}
    0.49
     mă
    0.48
     evaluation
    0.47
    ]++;
    0.46
     ordinal
    0.46
     അറിയ
    0.46
     appraisal
    0.45
    Act Density 0.001%

    No Known Activations