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

    Neuronpedia

    INDEX
    Explanations

    Python code and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    æld
    0.47
     Corporation
    0.47
     разо
    0.47
     Japan
    0.46
     Santiago
    0.46
     Stockholm
    0.46
     delas
    0.45
     Places
    0.44
     berada
    0.44
     Barcelona
    0.44
    POSITIVE LOGITS
    Liability
    0.47
    ች
    0.46
    EMPTY
    0.46
    क्के
    0.46
    پیگنڈ
    0.46
    liability
    0.46
    𝘔
    0.46
     brillant
    0.44
    يك
    0.44
    ంథ
    0.44
    Act Density 0.001%

    No Known Activations