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

    Neuronpedia

    INDEX
    Explanations

    Direction, only, weekly, behaviors, components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    外部リンク
    0.46
     fluctuate
    0.41
    ར
    0.40
    deficit
    0.39
    isive
    0.39
     fluctuates
    0.39
     Gog
    0.39
    cznie
    0.38
    getEntity
    0.37
     Federation
    0.37
    POSITIVE LOGITS
     }^{+}$
    0.49
     hospitality
    0.40
     viewport
    0.39
     communicating
    0.37
    náv
    0.37
     communicates
    0.36
     lanzar
    0.36
     ልዩ
    0.36
     strategia
    0.36
     magnificence
    0.36
    Act Density 0.000%

    No Known Activations