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

    Neuronpedia

    INDEX
    Explanations

    weighting with double colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ante
    0.42
     показывает
    0.42
    ève
    0.39
     जुड़े
    0.39
    Agen
    0.39
     membrana
    0.39
    coll
    0.38
    Functional
    0.38
    AutoGen
    0.37
     voir
    0.37
    POSITIVE LOGITS
    znych
    0.37
    ेंगे
    0.36
     वाइड
    0.36
    微
    0.36
     indices
    0.36
    更高
    0.36
    жни
    0.36
     ]:
    0.36
     রি
    0.36
     ':'
    0.36
    Act Density 0.000%

    No Known Activations