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

    Neuronpedia

    INDEX
    Explanations

    unexpected plot twists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acch
    0.43
    textAppearance
    0.40
    呟
    0.39
    හාර
    0.38
     discourses
    0.38
     देवगन
    0.38
     가능하다
    0.38
    firmasi
    0.37
    RACT
    0.37
     feas
    0.37
    POSITIVE LOGITS
     folks
    0.40
     hunters
    0.40
     Coupling
    0.39
     wristwatch
    0.39
     Plea
    0.39
     coupling
    0.38
     too
    0.37
     novella
    0.37
     detailing
    0.37
     portraits
    0.37
    Act Density 0.000%

    No Known Activations