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

    Neuronpedia

    INDEX
    Explanations

    Shake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bairro
    -0.08
     optimism
    -0.06
    ompson
    -0.06
     Commonwealth
    -0.06
     murdered
    -0.06
     οποία
    -0.06
     electoral
    -0.06
    oleč
    -0.06
    upos
    -0.06
     vistas
    -0.06
    POSITIVE LOGITS
    커
    0.07
    摇
    0.07
     �
    0.07
     جامعه
    0.07
     Outline
    0.07
    옥
    0.07
     キ
    0.07
    HING
    0.07
    티
    0.06
    čí
    0.06
    Act Density 0.006%

    No Known Activations