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

    Neuronpedia

    INDEX
    Explanations

    convey the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    For
    0.49
    Control
    0.49
    Outcome
    0.49
    र
    0.47
    राम
    0.47
     Conversely
    0.47
    不过
    0.46
    ט
    0.43
    紓
    0.43
    א
    0.42
    POSITIVE LOGITS
     scientist
    0.51
     beauties
    0.51
     chefs
    0.50
     explot
    0.50
     degrad
    0.50
     vulgar
    0.49
     microns
    0.48
     enzym
    0.48
     starch
    0.48
     extravag
    0.47
    Act Density 0.010%

    No Known Activations