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

    Neuronpedia

    INDEX
    Explanations

    mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fé
    -0.08
    ォ
    -0.07
     shout
    -0.06
    必须
    -0.06
    importe
    -0.06
    เภ
    -0.06
    ϊ
    -0.06
    UserProfile
    -0.06
    jin
    -0.06
     tôi
    -0.06
    POSITIVE LOGITS
    .rstrip
    0.06
     emission
    0.06
    unge
    0.06
     Gilles
    0.06
     subsequently
    0.06
     AudioSource
    0.06
    ора
    0.06
     uni
    0.06
    .expand
    0.06
     hovered
    0.06
    Act Density 0.009%

    No Known Activations