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

    Neuronpedia

    INDEX
    Explanations

    warranty disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lake
    -0.08
    ，从
    -0.07
     Disease
    -0.07
     walks
    -0.07
    Forest
    -0.06
     Cad
    -0.06
     Beard
    -0.06
     Archer
    -0.06
    Price
    -0.06
     surrounded
    -0.06
    POSITIVE LOGITS
     homosexual
    0.07
    anggan
    0.06
     тис
    0.06
    ственные
    0.06
     كبير
    0.06
    sil
    0.06
     amazingly
    0.06
    meye
    0.06
    ethoven
    0.06
    œ
    0.06
    Act Density 0.005%

    No Known Activations