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

    Neuronpedia

    INDEX
    Explanations

    feeling

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on Italian first-person-singular imperfect verb forms (verbs ending in “-vo,” e.g., “sentivo”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Nx
    -0.07
    Elite
    -0.07
     birkaç
    -0.07
    elpers
    -0.07
    _INITIAL
    -0.07
     yaptır
    -0.06
    Use
    -0.06
     Between
    -0.06
     fé
    -0.06
    uffer
    -0.06
    POSITIVE LOGITS
     overshadow
    0.06
     防
    0.06
     sensed
    0.06
     sac
    0.06
     кот
    0.06
     evac
    0.06
     мі
    0.06
     Colon
    0.06
     замен
    0.06
     discontent
    0.06
    Act Density 0.040%

    No Known Activations