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

    Neuronpedia

    INDEX
    Explanations

    combinations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Grid
    -0.07
    orary
    -0.07
    .rooms
    -0.06
     ruku
    -0.06
    urrenc
    -0.06
    '].'/
    -0.06
     OpCode
    -0.06
    �
    -0.06
     perennial
    -0.06
    週
    -0.06
    POSITIVE LOGITS
    latent
    0.07
     PT
    0.06
     bh
    0.06
     southeastern
    0.06
     الشر
    0.06
    도를
    0.06
     همراه
    0.06
     مراج
    0.06
    ()?;↵
    0.06
    ymbols
    0.06
    Act Density 0.036%

    No Known Activations