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

    Neuronpedia

    INDEX
    Explanations

    Sauron's power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ланы
    0.45
     Noeud
    0.45
    ienste
    0.44
    VENTION
    0.43
    ANDS
    0.42
    离开了
    0.42
     ಗುರು
    0.41
    recruit
    0.40
     Wanderers
    0.40
    ischem
    0.39
    POSITIVE LOGITS
    Section
    0.44
    r
    0.42
     debates
    0.39
    c
    0.38
     सीआर
    0.38
    glyphicon
    0.38
    हमारी
    0.37
    Online
    0.36
    online
    0.36
     arxivləşdirilib
    0.36
    Act Density 0.206%

    No Known Activations