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

    Neuronpedia

    INDEX
    Explanations

    login

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ref
    -0.07
     andere
    -0.07
     nex
    -0.07
    iyorlar
    -0.07
     mi
    -0.07
    partners
    -0.06
     alunos
    -0.06
     Abraham
    -0.06
    ял
    -0.06
     reven
    -0.06
    POSITIVE LOGITS
     reflecting
    0.08
     Silent
    0.07
    οντας
    0.07
     Ever
    0.07
     gint
    0.07
    split
    0.06
     dòng
    0.06
     annot
    0.06
     annotated
    0.06
     cinematic
    0.06
    Act Density 0.012%

    No Known Activations