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

    Neuronpedia

    INDEX
    Explanations

    disabled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CCT
    -0.06
     Accom
    -0.06
     luxurious
    -0.06
    灯火
    -0.06
    asse
    -0.06
    igious
    -0.06
    _RESP
    -0.06
    Mission
    -0.06
    फ
    -0.06
    abb
    -0.06
    POSITIVE LOGITS
     حت
    0.08
    .Monad
    0.08
    决议
    0.07
    -widgets
    0.07
     glu
    0.07
    .NO
    0.06
    귓
    0.06
     Manny
    0.06
     cognitive
    0.06
     abilities
    0.06
    Act Density 0.001%

    No Known Activations