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

    Neuronpedia

    INDEX
    Explanations

    code and makeup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⓘ
    0.39
    foration
    0.38
    Proveedor
    0.38
    icano
    0.37
    ovač
    0.37
     ومرحبا
    0.37
     ছু
    0.37
     Covering
    0.36
     Örneğin
    0.36
    ováno
    0.36
    POSITIVE LOGITS
    ிலும்
    0.44
     crowdfunding
    0.41
     shipwreck
    0.40
     exclusion
    0.40
     dals
    0.39
     masculin
    0.39
     chocolates
    0.38
     hacked
    0.38
     elbows
    0.38
    рная
    0.38
    Act Density 0.003%

    No Known Activations