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

    Neuronpedia

    INDEX
    Explanations

    Code and atypical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WebControls
    -0.47
     Lank
    -0.46
     ferr
    -0.45
    astéroïdes
    -0.44
    ent
    -0.44
     expired
    -0.43
     Mill
    -0.43
    al
    -0.42
    qtype
    -0.42
     mer
    -0.42
    POSITIVE LOGITS
    +#+#
    0.92
    AutoScale
    0.70
    Personendaten
    0.60
    ipedi
    0.59
     Réponses
    0.59
    openzeppelin
    0.58
    SEGUIR
    0.56
     jadx
    0.56
    ypeł
    0.55
    Xna
    0.55
    Act Density 0.000%

    No Known Activations