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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    The neuron activates on short English prepositions (like “in,” “at,” “on”) that introduce locative or temporal phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    риф
    -0.07
    TURN
    -0.06
    WithData
    -0.06
    shint
    -0.06
     tup
    -0.06
     �
    -0.06
    RestController
    -0.06
    رس
    -0.06
     мол
    -0.06
    _FORWARD
    -0.06
    POSITIVE LOGITS
     sonrası
    0.07
     [+
    0.07
    .pre
    0.06
    _poly
    0.06
    Stone
    0.06
    .Cos
    0.06
    ráž
    0.06
     varias
    0.06
     duvar
    0.06
     Occup
    0.06
    Act Density 0.595%

    No Known Activations