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

    Neuronpedia

    INDEX
    Explanations

    numerical sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spielt
    0.50
    。”
    0.50
    。『
    0.49
    AX
    0.49
    Ax
    0.46
    。「
    0.45
    у
    0.45
    。」
    0.45
    그
    0.45
    ပါတယ်။
    0.45
    POSITIVE LOGITS
     Watson
    0.46
     frustration
    0.45
     Prison
    0.45
     clearer
    0.43
     instrucciones
    0.43
     Sharon
    0.42
     prison
    0.42
     frustrations
    0.42
    0.42
     jail
    0.41
    Act Density 0.005%

    No Known Activations