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

    Neuronpedia

    INDEX
    Explanations

    and informational purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Materials
    0.86
     без
    0.85
    Materials
    0.78
     use
    0.78
     Without
    0.77
     flight
    0.76
    Without
    0.76
    icro
    0.76
     gulf
    0.74
     purposes
    0.73
    POSITIVE LOGITS
     emoc
    0.79
     amiga
    0.72
     emozioni
    0.69
    gum
    0.68
     upaya
    0.68
    我很
    0.68
     saluran
    0.67
     văn
    0.67
    early
    0.66
    button
    0.66
    Act Density 0.008%

    No Known Activations