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

    Neuronpedia

    INDEX
    Explanations

    memory address references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FORM
    0.51
    }.
    0.50
    同時に
    0.50
    ().
    0.49
    NOUNC
    0.49
     способом
    0.49
    ONU
    0.48
     مسئله
    0.47
     طریقہ
    0.47
     सांगितले
    0.47
    POSITIVE LOGITS
    gaan
    0.52
    tempat
    0.51
    షా
    0.51
     militares
    0.50
    grö
    0.49
    Permalink
    0.47
     militar
    0.47
    gas
    0.47
    c
    0.46
     veer
    0.45
    Act Density 0.000%

    No Known Activations