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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keeping
    -0.06
     Woo
    -0.06
    Weights
    -0.06
     Supporters
    -0.06
     Plumbing
    -0.06
    μερο
    -0.06
     mediums
    -0.06
    农业
    -0.06
     Intermediate
    -0.06
     Cinder
    -0.06
    POSITIVE LOGITS
     действия
    0.06
    sav
    0.06
    verages
    0.06
     climb
    0.06
    ()):
    0.06
    ippo
    0.06
     manual
    0.06
    換
    0.06
     shutdown
    0.06
     zones
    0.06
    Act Density 0.000%

    No Known Activations