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

    Neuronpedia

    INDEX
    Explanations

    being held back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ->↵
    -0.07
    -li
    -0.07
     년도별
    -0.07
    rical
    -0.06
    _rd
    -0.06
    .addValue
    -0.06
    ?',
    -0.06
    ()">↵
    -0.06
    _STOCK
    -0.06
     Siemens
    -0.06
    POSITIVE LOGITS
     Mao
    0.08
     жид
    0.07
    жа
    0.07
     TNT
    0.06
     aload
    0.06
     assurance
    0.06
     SMART
    0.06
     technique
    0.06
     conscient
    0.06
    iền
    0.06
    Act Density 0.022%

    No Known Activations