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

    Neuronpedia

    INDEX
    Explanations

    introducing discussions or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ring
    0.45
     MC
    0.45
     MX
    0.45
     AV
    0.45
     club
    0.43
    9
    0.43
     al
    0.43
    th
    0.42
     du
    0.42
     AN
    0.42
    POSITIVE LOGITS
    ගෙන
    0.48
    ibalsan
    0.47
    ᵚ
    0.46
    해주
    0.45
    zeniu
    0.43
    Pré
    0.43
    हट
    0.43
    žený
    0.43
    Correo
    0.42
    deme
    0.42
    Act Density 0.002%

    No Known Activations