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

    Neuronpedia

    INDEX
    Explanations

    present state descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পাট
    0.60
    讓
    0.59
     interested
    0.57
     kife
    0.55
     appeal
    0.54
     Wasch
    0.54
    шава
    0.53
    是不是
    0.52
     поводу
    0.51
    했
    0.51
    POSITIVE LOGITS
    carrying
    0.57
     بالاتر
    0.56
     richer
    0.55
     కార్
    0.54
    ແ
    0.53
     దగ్
    0.53
     caterpillars
    0.52
     {}
    0.51
     wilde
    0.50
     editor
    0.50
    Act Density 0.104%

    No Known Activations