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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Estonia
    -0.08
    .trim
    -0.07
    zej
    -0.06
     Bender
    -0.06
    untu
    -0.06
    桥
    -0.06
     Belg
    -0.06
    _small
    -0.06
    -layer
    -0.06
     cliffs
    -0.06
    POSITIVE LOGITS
     dire
    0.07
    support
    0.07
     medical
    0.06
     recon
    0.06
    관련
    0.06
    School
    0.06
    _ORIENTATION
    0.06
     můžeme
    0.06
     řed
    0.06
     مقر
    0.06
    Act Density 0.008%

    No Known Activations