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

    Neuronpedia

    INDEX
    Explanations

    complex structures and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    managedbuild
    0.42
    受験
    0.42
     AMERICA
    0.42
    ﺂ
    0.41
     riding
    0.41
     Crank
    0.40
    Princess
    0.40
    gående
    0.38
     ILLUSTR
    0.38
    vide
    0.38
    POSITIVE LOGITS
     التمثيل
    0.39
     sing
    0.37
    歸
    0.36
     prad
    0.36
    чет
    0.35
    െ
    0.35
     inst
    0.34
     lord
    0.34
     kull
    0.33
    ômios
    0.33
    Act Density 0.018%

    No Known Activations