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

    Neuronpedia

    INDEX
    Explanations

    Contrast/Contradiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cancell
    -0.08
     roup
    -0.08
     invitations
    -0.07
     tood
    -0.07
     Tripadvisor
    -0.07
    zego
    -0.07
     vap
    -0.07
     vagu
    -0.07
    оточ
    -0.07
    ansyon
    -0.07
    POSITIVE LOGITS
    Jump
    0.08
    uban
    0.08
    _bl
    0.07
     превыш
    0.07
    _MASK
    0.07
    Reached
    0.07
     jump
    0.07
    _jump
    0.07
     отличаются
    0.07
    _until
    0.07
    Act Density 0.073%

    No Known Activations