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

    Neuronpedia

    INDEX
    Explanations

    team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chester
    -0.06
     poignant
    -0.06
    ницу
    -0.06
     trí
    -0.06
     quiere
    -0.06
     pee
    -0.06
     sees
    -0.06
     instit
    -0.06
    онь
    -0.05
     카
    -0.05
    POSITIVE LOGITS
     souls
    0.08
    εργ
    0.08
     Marlins
    0.08
     evitar
    0.07
     Generate
    0.07
    _YELLOW
    0.07
    -arm
    0.07
    살
    0.07
     Language
    0.07
     certainty
    0.07
    Act Density 0.000%

    No Known Activations