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

    Neuronpedia

    INDEX
    Explanations

    Western Digital, WireGuard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uencia
    0.40
     inim
    0.40
    unzione
    0.39
    ুনিক
    0.39
    uasion
    0.39
    ific
    0.39
    uncan
    0.38
    総合
    0.38
    apayati
    0.38
    珼
    0.38
    POSITIVE LOGITS
     WL
    0.62
     W
    0.58
     WD
    0.58
     AW
    0.55
     WBC
    0.53
     WC
    0.51
     VW
    0.50
    Ꮃ
    0.50
     PW
    0.49
    डब्ल्यू
    0.49
    Act Density 0.082%

    No Known Activations