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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron doesn’t respond to any tokens (i.e. it’s effectively inactive or “dead”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Former
    -0.06
     Nobel
    -0.06
    ting
    -0.06
     fadeIn
    -0.06
    Aceptar
    -0.06
     guests
    -0.06
    startsWith
    -0.06
     murder
    -0.06
    都会
    -0.06
     příslu
    -0.06
    POSITIVE LOGITS
     ",");↵
    0.07
     Wooden
    0.07
    ,.
    0.06
    (system
    0.06
     are
    0.06
     Howell
    0.06
     styleUrls
    0.06
    ideo
    0.06
    izzard
    0.06
     disin
    0.06
    Act Density 0.023%

    No Known Activations