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

    Neuronpedia

    INDEX
    Explanations

    responses to diverse activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Merging
    1.16
    प्ट
    1.14
     diaria
    1.14
     chir
    1.05
    물
    1.05
    毛
    1.02
    з
    1.02
    裟
    0.99
     ${\
    0.99
     chez
    0.96
    POSITIVE LOGITS
     веществ
    1.27
     تعداد
    1.15
    Ngoài
    1.14
     zákon
    1.13
    cmb
    1.13
     پس
    1.13
     солдат
    1.11
     UpdateWindow
    1.11
     ограничењима
    1.11
     orchards
    1.11
    Act Density 0.000%

    No Known Activations