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

    Neuronpedia

    INDEX
    Explanations

    online services and APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pr
    0.57
     consume
    0.56
     Neither
    0.54
    なんで
    0.53
     응
    0.51
     pass
    0.51
    께서
    0.50
     ak
    0.49
     cause
    0.49
     inher
    0.49
    POSITIVE LOGITS
    odesk
    1.00
    Monster
    0.95
    Logic
    0.89
    itec
    0.87
    zilla
    0.87
    മസ
    0.86
    ogo
    0.86
    monster
    0.86
    GPT
    0.85
    ify
    0.85
    Act Density 0.182%

    No Known Activations