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

    Neuronpedia

    INDEX
    Explanations

    literacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Literacy
    -0.95
     literacy
    -0.94
     énergé
    -0.93
    Literacy
    -0.91
    __':
    -0.85
     lumineuse
    -0.82
     varandra
    -0.80
     créativité
    -0.80
     fédé
    -0.79
    utilisons
    -0.78
    POSITIVE LOGITS
     and
    0.65
    ,
    0.58
    less
    0.58
    ase
    0.57
    ly
    0.54
     (
    0.54
    land
    0.52
     associated
    0.51
    stal
    0.49
    .
    0.49
    Act Density 0.065%

    No Known Activations