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

    Neuronpedia

    INDEX
    Explanations

    professional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     head
    -0.07
    /read
    -0.07
     compute
    -0.07
     heads
    -0.06
     tweaks
    -0.06
     window
    -0.06
     crew
    -0.06
     ro
    -0.06
     shell
    -0.06
     com
    -0.06
    POSITIVE LOGITS
    peats
    0.07
    arbonate
    0.07
    Я
    0.07
    tablet
    0.06
     �
    0.06
     CONSTANT
    0.06
    Detector
    0.06
     invitations
    0.06
    šker
    0.06
    INATION
    0.06
    Act Density 0.019%

    No Known Activations