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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “That
    -0.07
     IDirect
    -0.07
    Factory
    -0.07
    .Registry
    -0.07
     cropped
    -0.07
     conservatives
    -0.07
    ycastle
    -0.07
     used
    -0.07
     target
    -0.07
    -Sep
    -0.07
    POSITIVE LOGITS
    InnerHTML
    0.06
    urrenc
    0.06
    charges
    0.06
    حدث
    0.06
    ■■
    0.06
    OrNull
    0.06
    ement
    0.06
    ）は
    0.06
     засід
    0.06
     GRAT
    0.06
    Act Density 0.018%

    No Known Activations