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

    Neuronpedia

    INDEX
    Explanations

    1-800-656-HOPE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Catawiki
    0.54
     totalSupply
    0.50
     optimised
    0.47
     regenerated
    0.46
     polarisation
    0.46
     trivially
    0.45
    第壹百
    0.45
     polarised
    0.45
     globalisation
    0.44
     deprecated
    0.43
    POSITIVE LOGITS
     referral
    1.05
     referrals
    1.05
     crisis
    1.04
     counselors
    1.00
     Crisis
    0.95
     Referral
    0.93
    crisis
    0.93
    Crisis
    0.92
     кризи
    0.91
     hotline
    0.91
    Act Density 0.253%

    No Known Activations