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

    Neuronpedia

    INDEX
    Explanations

    lists, sequences, or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ама
    0.47
     enfer
    0.46
     malé
    0.46
     nang
    0.45
     бара
    0.45
     gdf
    0.44
     bajo
    0.44
     toi
    0.44
     Barney
    0.44
     vc
    0.44
    POSITIVE LOGITS
    sciences
    0.51
    nes
    0.50
    strategies
    0.49
    uminescence
    0.48
    sa
    0.48
    changes
    0.48
    csv
    0.47
    Y
    0.47
    termination
    0.46
    क्रि
    0.46
    Act Density 0.044%

    No Known Activations