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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ien
    -0.07
    -media
    -0.07
    .codehaus
    -0.07
     jamais
    -0.07
     Türkçe
    -0.07
    Fields
    -0.06
    �
    -0.06
     New
    -0.06
     reassure
    -0.06
    Dan
    -0.06
    POSITIVE LOGITS
    뎀
    0.07
    👆
    0.07
    erequisite
    0.07
    עלי
    0.07
    expo
    0.07
    �
    0.07
    }}{{
    0.06
    客气
    0.06
     obligatory
    0.06
    -serif
    0.06
    Act Density 0.018%

    No Known Activations