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

    Neuronpedia

    INDEX
    Explanations

    volunteering and helping others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chromat
    0.42
     encrypted
    0.36
    itious
    0.35
     paranoid
    0.35
     iphdr
    0.35
    oforte
    0.34
    {
    0.34
     prematurely
    0.34
    setMax
    0.34
    encrypted
    0.33
    POSITIVE LOGITS
     volunteer
    3.16
     volunteering
    3.05
     volunteers
    2.89
     Volunteer
    2.88
    Volunteer
    2.84
    volunteer
    2.80
     Volunte
    2.75
     Volunteers
    2.61
    志愿者
    2.50
     volunte
    2.42
    Act Density 0.011%

    No Known Activations