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

    Neuronpedia

    INDEX
    Explanations

    dependence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uslim
    -0.07
     Sikh
    -0.07
     layui
    -0.07
    median
    -0.07
     Ket
    -0.06
     목
    -0.06
    ickým
    -0.06
     thủy
    -0.06
    _meas
    -0.06
     mesh
    -0.06
    POSITIVE LOGITS
    番組
    0.07
    (va
    0.06
    Ｋ
    0.06
    ROLL
    0.06
     agreeing
    0.06
    chemical
    0.06
    โทร
    0.06
    ativity
    0.06
     getC
    0.06
     stanice
    0.06
    Act Density 0.009%

    No Known Activations