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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wechat
    -0.07
    原因
    -0.07
    Haz
    -0.07
    _LEVEL
    -0.07
    แรง
    -0.07
     policeman
    -0.07
    Dictionary
    -0.07
    än
    -0.06
     ancor
    -0.06
    융
    -0.06
    POSITIVE LOGITS
     eff
    0.07
     poss
    0.07
    �
    0.06
     stylish
    0.06
     也
    0.06
     اف
    0.06
    รร
    0.05
    :f
    0.05
    елеф
    0.05
     коман
    0.05
    Act Density 0.006%

    No Known Activations