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

    Neuronpedia

    INDEX
    Explanations

    python code frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ausea
    0.70
     unreasonable
    0.67
    膊
    0.67
    verlet
    0.66
    pxy
    0.66
    ålet
    0.64
    ribly
    0.63
     sadistic
    0.62
     alır
    0.61
    avax
    0.61
    POSITIVE LOGITS
     dieser
    0.64
     underlines
    0.61
    段階
    0.61
     Cette
    0.61
     Dieser
    0.60
    このような
    0.60
    这不是
    0.60
     compounds
    0.59
     وهذه
    0.59
     Extending
    0.58
    Act Density 0.051%

    No Known Activations