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

    Neuronpedia

    INDEX
    Explanations

    Frivolous

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the root “frivol” (as in “frivolous”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    AGIC
    -0.07
     submission
    -0.07
    issent
    -0.07
     shorter
    -0.07
    agic
    -0.07
    .Return
    -0.06
     Seek
    -0.06
     وقد
    -0.06
     розроб
    -0.06
     Replace
    -0.06
    POSITIVE LOGITS
    Frozen
    0.07
     fridge
    0.06
    лина
    0.06
     frivol
    0.06
     amphib
    0.06
     Possibly
    0.06
     süresi
    0.06
     Frozen
    0.06
     Carnival
    0.06
     <>↵
    0.06
    Act Density 0.000%

    No Known Activations