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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    痼
    -0.07
     confirmed
    -0.07
    _grp
    -0.07
    abd
    -0.06
    wn
    -0.06
    ppe
    -0.06
    可视化
    -0.06
    نعم
    -0.06
    emy
    -0.06
    -town
    -0.06
    POSITIVE LOGITS
     HRESULT
    0.07
    铗
    0.07
    dıktan
    0.07
     necesario
    0.07
    :NSLayout
    0.07
    itespace
    0.07
     OUT
    0.07
     system
    0.07
    んですよね
    0.07
     They
    0.07
    Act Density 0.007%

    No Known Activations