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

    Neuronpedia

    INDEX
    Explanations

    goddamnGodgodsend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ations
    0.68
     soliton
    0.67
     агре
    0.66
     Notify
    0.66
     legale
    0.65
     arrears
    0.64
     거
    0.64
     idiopathic
    0.63
     modifications
    0.63
     perpetuity
    0.61
    POSITIVE LOGITS
     forbid
    1.53
    damn
    1.52
     bless
    1.51
     Almighty
    1.48
     Bless
    1.35
     almighty
    1.33
    Bless
    1.29
    send
    1.24
    rej
    1.19
     blessing
    1.17
    Act Density 0.022%

    No Known Activations