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

    Neuronpedia

    INDEX
    Explanations

    Javascript code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    connexion
    -0.07
    疝
    -0.07
     emb
    -0.07
     Cambodia
    -0.07
     beet
    -0.07
     lựa
    -0.06
     sek
    -0.06
     Falk
    -0.06
    峡
    -0.06
     unanim
    -0.06
    POSITIVE LOGITS
    _street
    0.08
    .sprites
    0.07
    _break
    0.07
    	df
    0.07
    achines
    0.07
    logfile
    0.07
    _ground
    0.07
    まぁ
    0.06
     oferta
    0.06
    >".
    0.06
    Act Density 0.004%

    No Known Activations