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

    Neuronpedia

    INDEX
    Explanations

    sentiment and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    資金
    0.39
    cies
    0.38
     inp
    0.37
    墾
    0.37
     AGRIC
    0.36
     肌
    0.36
    讖
    0.36
     σκο
    0.36
    фере
    0.36
    \<^
    0.35
    POSITIVE LOGITS
     hadden
    0.42
     Haunted
    0.41
     treating
    0.40
     homestead
    0.40
     flap
    0.39
     Emotion
    0.39
    Emotional
    0.39
     Emotional
    0.38
     Emotions
    0.37
     emotions
    0.37
    Act Density 0.000%

    No Known Activations