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

    Neuronpedia

    INDEX
    Explanations

    problems and solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lichting
    0.50
     временем
    0.48
    <unused573>
    0.48
     даже
    0.47
    ügen
    0.47
     thậm
    0.46
    ieve
    0.46
    äns
    0.46
     cải
    0.46
    ienten
    0.45
    POSITIVE LOGITS
     problems
    0.47
     unlawful
    0.46
     Problems
    0.45
     accolades
    0.44
     Songs
    0.43
    Q
    0.42
     worship
    0.42
     constituents
    0.41
     entities
    0.41
     allegations
    0.41
    Act Density 0.006%

    No Known Activations