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

    Neuronpedia

    INDEX
    Explanations

    error at or near

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lime
    0.44
    Lime
    0.38
     []
    0.38
    рию
    0.38
     NSDictionary
    0.37
    ުން
    0.37
     விநாயக
    0.37
     ܡ
    0.36
    innerApiCalls
    0.36
    场的
    0.36
    POSITIVE LOGITS
    barg
    0.39
    feitos
    0.37
    Planck
    0.37
    osse
    0.36
    mixture
    0.36
    jas
    0.35
    newpage
    0.35
    '];
    0.35
     liberdade
    0.35
     marbled
    0.35
    Act Density 0.000%

    No Known Activations