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

    Neuronpedia

    INDEX
    Explanations

    pain relief/anxiety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ukup
    0.41
     buddh
    0.39
     endow
    0.39
    strates
    0.38
     vak
    0.38
     TAC
    0.38
     bandits
    0.38
    ələ
    0.37
     Ata
    0.37
     isoform
    0.37
    POSITIVE LOGITS
    废水
    0.44
    Guard
    0.41
     इवन
    0.40
    凤
    0.38
    alos
    0.38
    柔
    0.37
    沤
    0.36
     consisted
    0.36
    Practical
    0.36
    Buyer
    0.36
    Act Density 0.001%

    No Known Activations