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

    Neuronpedia

    INDEX
    Explanations

    thoughts and speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thái
    -0.07
    Animation
    -0.06
    513
    -0.06
    bes
    -0.06
     merkez
    -0.06
     muh
    -0.06
    ToDelete
    -0.06
    710
    -0.06
     Sağlık
    -0.06
     vídeos
    -0.06
    POSITIVE LOGITS
    δυ
    0.06
    ened
    0.06
     profil
    0.06
    �
    0.06
     хви
    0.06
     kvp
    0.06
     Persona
    0.06
     neben
    0.06
     }))↵
    0.06
     outer
    0.06
    Act Density 0.153%

    No Known Activations