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

    Neuronpedia

    INDEX
    Explanations

    sending messages or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seductive
    0.38
     sedative
    0.38
     authoritarian
    0.35
     sedation
    0.35
    দিনী
    0.35
     reactionary
    0.34
     disturbs
    0.34
     delusional
    0.34
    菪
    0.34
     militias
    0.33
    POSITIVE LOGITS
    N
    0.34
    e
    0.33
    op
    0.32
    C
    0.32
    Check
    0.31
    M
    0.31
    T
    0.30
    G
    0.29
    c
    0.28
    al
    0.28
    Act Density 0.000%

    No Known Activations