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

    Neuronpedia

    INDEX
    Explanations

    Later interpretations, which necessitate, people learn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APPY
    0.48
    Trains
    0.45
     intervalles
    0.45
    requent
    0.44
     зі
    0.44
    🎩
    0.44
    ді
    0.43
    APH
    0.43
    issantes
    0.43
     testname
    0.43
    POSITIVE LOGITS
     humor
    0.49
     courage
    0.46
     sarcasm
    0.46
     discord
    0.46
     also
    0.45
     courrier
    0.45
     misunder
    0.44
     deriv
    0.43
     reverb
    0.43
     opinion
    0.43
    Act Density 0.007%

    No Known Activations