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

    Neuronpedia

    INDEX
    Explanations

    align with human values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ورية
    0.42
    集成
    0.41
     interplay
    0.39
     دليل
    0.39
    dil
    0.38
    d
    0.38
     பிரமி
    0.38
     свя
    0.37
     Tired
    0.37
    Granted
    0.37
    POSITIVE LOGITS
     aligning
    1.34
     alignment
    1.31
     aligned
    1.26
     align
    1.20
     Alignment
    1.20
     Align
    1.18
     aligns
    1.16
    Align
    1.10
    align
    1.09
    alignment
    1.09
    Act Density 0.007%

    No Known Activations