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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ethics
    -0.07
    esters
    -0.06
    ापन
    -0.06
    lerinde
    -0.06
     asynchronously
    -0.06
     cabin
    -0.06
     mozilla
    -0.06
    abble
    -0.06
    匹
    -0.06
    Phot
    -0.06
    POSITIVE LOGITS
    outed
    0.07
     regularization
    0.06
     річ
    0.06
     traj
    0.06
    شهر
    0.06
     Fran
    0.06
     Kraj
    0.06
     구글상위
    0.06
    iet
    0.06
     wiel
    0.06
    Act Density 0.035%

    No Known Activations