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

    Neuronpedia

    INDEX
    Explanations

    would you like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     love
    0.74
     joy
    0.72
     adore
    0.71
     mistrust
    0.70
     happily
    0.70
     distrust
    0.69
    爱
    0.68
     LOVE
    0.67
     suspect
    0.67
     happiest
    0.67
    POSITIVE LOGITS
     like
    0.68
     Like
    0.67
    Like
    0.65
    like
    0.64
    would
    0.64
    lysninger
    0.64
    Would
    0.64
    یدار
    0.63
    Eden
    0.63
    gegevens
    0.63
    Act Density 0.116%

    No Known Activations