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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Red
    -0.07
     dir
    -0.07
     milieu
    -0.06
    _gen
    -0.06
    Robin
    -0.06
     Vak
    -0.06
    	conf
    -0.06
    کم
    -0.06
     Nag
    -0.06
     통해
    -0.06
    POSITIVE LOGITS
    .Here
    0.06
     lobby
    0.06
    INAL
    0.06
     Cette
    0.06
    داری
    0.06
    окумент
    0.06
    (short
    0.06
     Compare
    0.06
     Assigned
    0.06
     Lobby
    0.06
    Act Density 0.003%

    No Known Activations