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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     statusBar
    -0.08
     should
    -0.07
    ot
    -0.07
     must
    -0.07
    *r
    -0.07
     Scroll
    -0.07
     knowing
    -0.07
    _Not
    -0.07
    .Padding
    -0.06
     gotta
    -0.06
    POSITIVE LOGITS
     these
    0.19
     These
    0.17
    These
    0.16
    “These
    0.14
    these
    0.14
     THESE
    0.13
    "These
    0.12
     estos
    0.10
    ні
    0.09
    PE
    0.09
    Act Density 0.088%

    No Known Activations