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

    Neuronpedia

    INDEX
    Explanations

    inspirational positive life reflections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sadistic
    0.58
     depressing
    0.51
     paranoid
    0.51
     paranoia
    0.51
     halluc
    0.46
     malaise
    0.46
     demonic
    0.46
     excitation
    0.46
     brooding
    0.46
     amusing
    0.45
    POSITIVE LOGITS
    💛
    0.71
    💙
    0.60
     💕
    0.58
    ❤️
    0.55
     kindness
    0.55
     💞
    0.55
    💕
    0.54
    ♥️
    0.53
    Healing
    0.53
     ❤
    0.53
    Act Density 0.039%

    No Known Activations