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

    Neuronpedia

    INDEX
    Explanations

    separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     这
    -0.07
     DSP
    -0.07
    ↵↵↵↵↵↵↵↵↵
    -0.07
     trở
    -0.06
    .capitalize
    -0.06
     hj
    -0.06
    jumbotron
    -0.06
    _Tree
    -0.06
    >O
    -0.06
     notation
    -0.06
    POSITIVE LOGITS
    ocaly
    0.06
    -middle
    0.06
    olv
    0.06
    .today
    0.06
     confinement
    0.06
    μάτων
    0.06
    dney
    0.06
     annex
    0.06
     Гер
    0.06
     मन
    0.06
    Act Density 0.157%

    No Known Activations