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

    Neuronpedia

    INDEX
    Explanations

    CU

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ⴝ
    -0.08
     wordt
    -0.07
    _waiting
    -0.07
     ByteBuffer
    -0.07
    🐫
    -0.07
    .banner
    -0.07
     Warcraft
    -0.07
    וידאו
    -0.07
    ,args
    -0.07
    ][$
    -0.07
    POSITIVE LOGITS
    -efficient
    0.08
     republic
    0.07
     Gur
    0.07
     ranch
    0.07
     persistence
    0.07
    -grid
    0.07
    颤
    0.07
     Fle
    0.07
     breaking
    0.07
    Split
    0.07
    Act Density 0.001%

    No Known Activations