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

    Neuronpedia

    INDEX
    Explanations

    Online chats and messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iu
    -0.07
    itives
    -0.06
    가는
    -0.06
     betrayal
    -0.06
     연결
    -0.06
     debilitating
    -0.06
    _campaign
    -0.06
    reveal
    -0.06
     крови
    -0.06
    @endif
    -0.06
    POSITIVE LOGITS
     byt
    0.07
     deterioration
    0.06
     duplication
    0.06
     Animalia
    0.06
     xl
    0.06
    .script
    0.06
     vým
    0.06
     enchant
    0.06
     genesis
    0.06
     Secure
    0.06
    Act Density 0.076%

    No Known Activations