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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ~,
    -0.07
     השל
    -0.07
    首
    -0.07
    _title
    -0.07
    包容
    -0.07
    delete
    -0.07
    主要
    -0.06
    _resources
    -0.06
    theless
    -0.06
    ᆢ
    -0.06
    POSITIVE LOGITS
     pessoa
    0.07
    比较高
    0.07
     예수님
    0.07
     Clippers
    0.07
     compartir
    0.07
    ("--------------------------------
    0.07
    culator
    0.07
     bitrate
    0.07
    环保
    0.07
    해야
    0.07
    Act Density 0.042%

    No Known Activations