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

    Neuronpedia

    INDEX
    Explanations

    intensification and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MBA
    0.49
    たちの
    0.47
     EXO
    0.43
    0.40
     Investigación
    0.40
    需求的
    0.39
     creación
    0.39
     Fiesta
    0.39
     Invasion
    0.38
     Organización
    0.38
    POSITIVE LOGITS
     grievous
    0.51
     önüne
    0.49
     unrelenting
    0.48
     unbear
    0.47
    lhe
    0.46
     relent
    0.45
     compounded
    0.45
    risto
    0.45
    mittent
    0.44
     exacerbated
    0.44
    Act Density 0.008%

    No Known Activations