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

    Neuronpedia

    INDEX
    Explanations

    Would you like me to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     me
    0.64
     mee
    0.59
     attn
    0.57
     ya
    0.55
     they
    0.54
     mre
    0.53
    foe
    0.52
     someth
    0.52
     ME
    0.51
     their
    0.50
    POSITIVE LOGITS
    Lorsque
    0.78
     Lorsque
    0.72
     عندما
    0.70
    Cuando
    0.68
     כאשר
    0.68
    하려고
    0.65
     sogenannte
    0.65
     lorsque
    0.63
     ಮಾಡುತ್ತ
    0.62
     протягом
    0.62
    Act Density 0.127%

    No Known Activations