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

    Neuronpedia

    INDEX
    Explanations

    threading issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ויש
    -0.08
    east
    -0.07
    入境
    -0.07
    .setEnabled
    -0.07
     wise
    -0.07
    raison
    -0.07
     şeklin
    -0.07
    -save
    -0.07
     יש
    -0.07
     элект
    -0.07
    POSITIVE LOGITS
    Temporal
    0.07
    不過
    0.07
    )!↵
    0.07
    bones
    0.07
     .
↵
    0.07
    𝙢
    0.07
    واشن
    0.07
    mega
    0.06
    覆盖
    0.06
    ATING
    0.06
    Act Density 0.043%

    No Known Activations