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

    Neuronpedia

    INDEX
    Explanations

    word fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pursuit
    -0.06
     tantr
    -0.06
     slander
    -0.06
     heed
    -0.06
    CharCode
    -0.06
    .KeyChar
    -0.06
     hữu
    -0.06
     Romanian
    -0.06
     yên
    -0.06
    iểm
    -0.06
    POSITIVE LOGITS
     Phil
    0.07
    oil
    0.07
    [this
    0.07
    Gl
    0.07
     даже
    0.06
    touch
    0.06
     portals
    0.06
    -as
    0.06
    marker
    0.06
    (full
    0.06
    Act Density 0.027%

    No Known Activations