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

    Neuronpedia

    INDEX
    Explanations

    legal and official terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olive
    0.57
     entfernen
    0.56
     technologie
    0.54
     cette
    0.54
     dapat
    0.54
     μια
    0.54
     joka
    0.53
    이에
    0.53
     Esta
    0.53
     daha
    0.53
    POSITIVE LOGITS
    讠
    0.50
    賏
    0.50
    媇
    0.48
    阠
    0.48
    पि
    0.48
    軎
    0.47
    㗆
    0.46
    驭
    0.46
    暊
    0.46
    !!.
    0.46
    Act Density 0.071%

    No Known Activations