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

    Neuronpedia

    INDEX
    Explanations

    Software tutorials/training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mimo
    -0.06
     メ
    -0.06
     tails
    -0.06
     dostate
    -0.06
    Ja
    -0.06
    ↓
    -0.06
    (xy
    -0.06
     fh
    -0.06
     ACTIONS
    -0.06
    ournée
    -0.06
    POSITIVE LOGITS
    IBOutlet
    0.07
     özellik
    0.06
     โรง
    0.06
     licensors
    0.06
     стор
    0.06
    іка
    0.06
     contenders
    0.06
    \admin
    0.06
     prosec
    0.06
    няв
    0.06
    Act Density 0.166%

    No Known Activations