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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases describing typical uses or purposes—e.g. “are often used to store and manipulate…”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cues
    -0.07
    ,number
    -0.06
     recieved
    -0.06
    .movies
    -0.06
    _FLOW
    -0.06
    aber
    -0.06
    vincia
    -0.06
    currentColor
    -0.06
    Similar
    -0.06
    ViewModel
    -0.06
    POSITIVE LOGITS
    時に
    0.07
    0.07
     Angie
    0.07
     teal
    0.06
     essentials
    0.06
     tome
    0.06
    210
    0.06
     conn
    0.06
    (k
    0.06
     tie
    0.06
    Act Density 0.045%

    No Known Activations