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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive—it never lights up for any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Shore
    -0.07
    осуд
    -0.07
     стара
    -0.06
    idge
    -0.06
     ряд
    -0.06
    .Instance
    -0.06
    aupt
    -0.06
    assis
    -0.06
    _ports
    -0.06
     buildup
    -0.06
    POSITIVE LOGITS
     by
    0.07
     perceive
    0.07
     Bush
    0.07
    NH
    0.07
    .Marker
    0.06
     Gill
    0.06
     excluding
    0.06
    فر
    0.06
     REPLACE
    0.06
    PROGRAM
    0.06
    Act Density 0.011%

    No Known Activations