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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    にして
    -0.07
    awah
    -0.07
    ucht
    -0.07
    YYY
    -0.07
    gif
    -0.07
     :=
    -0.06
    .Detail
    -0.06
     namespaces
    -0.06
     merged
    -0.06
    sheet
    -0.06
    POSITIVE LOGITS
     neoliberal
    0.06
    .grey
    0.06
     работу
    0.06
     plutôt
    0.06
     dell
    0.06
    EP
    0.06
     چشم
    0.06
    �
    0.06
    最後
    0.06
     непри
    0.06
    Act Density 0.064%

    No Known Activations