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

    Neuronpedia

    INDEX
    Explanations

    successes required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Revision
    0.39
    Reason
    0.39
     কারনে
    0.38
     Florida
    0.37
     Tort
    0.36
    riline
    0.36
     FLORIDA
    0.36
     ⿰
    0.35
     Absolute
    0.35
     ტი
    0.34
    POSITIVE LOGITS
     È
    0.41
     è
    0.39
     defendants
    0.37
    È
    0.37
     Félix
    0.36
     sout
    0.35
    インチ
    0.35
     wym
    0.35
     compartilh
    0.35
    ellae
    0.35
    Act Density 0.002%

    No Known Activations