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

    Neuronpedia

    INDEX
    Explanations

    code with symbols and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ආ
    0.44
     angiotensin
    0.43
    देन
    0.41
     coinage
    0.40
     mantra
    0.39
    био
    0.38
    нием
    0.38
     cytokines
    0.38
     penuh
    0.38
     advertising
    0.37
    POSITIVE LOGITS
    中心的
    0.42
    ্নের
    0.40
     બીજા
    0.38
    ()[
    0.36
    दूसरे
    0.35
    粓
    0.33
     दूसरे
    0.32
     Canc
    0.31
    வரது
    0.31
    自身の
    0.31
    Act Density 0.127%

    No Known Activations