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

    Neuronpedia

    INDEX
    Explanations

    kingdom of god

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lar
    0.95
     Clarke
    0.94
    Fal
    0.92
     CSA
    0.92
    Sa
    0.91
    sections
    0.91
    CSA
    0.91
    Clarke
    0.89
     Akin
    0.89
    Aqu
    0.89
    POSITIVE LOGITS
     Bernad
    1.02
     Thomson
    0.94
     Rhodes
    0.84
     Eastwood
    0.84
     Rosenthal
    0.80
     Prompt
    0.78
     Jagger
    0.78
     prompt
    0.77
     prick
    0.76
     punching
    0.74
    Act Density 2.018%

    No Known Activations