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

    Neuronpedia

    INDEX
    Explanations

    current events and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    constructed
    0.41
    crystalline
    0.40
    construct
    0.40
    Eddie
    0.40
    chemical
    0.39
    European
    0.39
    facial
    0.39
    decision
    0.38
    MODEL
    0.38
    Park
    0.38
    POSITIVE LOGITS
     सुमारे
    0.47
     从
    0.42
    💂
    0.42
     mengapa
    0.41
     ภาษา
    0.40
     грамо
    0.40
    🐊
    0.40
    🏇
    0.39
    大约
    0.39
    📚
    0.39
    Act Density 0.000%

    No Known Activations