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

    Neuronpedia

    INDEX
    Explanations

    technology related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .There
    -0.07
     низ
    -0.06
     Films
    -0.06
     Architect
    -0.06
    含
    -0.06
     sediment
    -0.06
     predatory
    -0.06
     regardless
    -0.06
    -rich
    -0.06
    博士
    -0.06
    POSITIVE LOGITS
     destructor
    0.06
     obtains
    0.06
    XE
    0.06
    .hasMore
    0.06
     مسئ
    0.06
    yum
    0.06
    ease
    0.06
    cases
    0.06
    RGBO
    0.06
    _adc
    0.06
    Act Density 0.177%

    No Known Activations