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

    Neuronpedia

    INDEX
    Explanations

    Anatomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     migration
    -0.07
    (it
    -0.06
    username
    -0.06
    -t
    -0.06
    quiv
    -0.06
    ]↵↵↵↵
    -0.06
    っている
    -0.06
    Accuracy
    -0.06
    _phrase
    -0.06
    -menu
    -0.06
    POSITIVE LOGITS
    SCRIPTOR
    0.07
     расч
    0.07
    INED
    0.07
    ीड
    0.06
    тий
    0.06
     практически
    0.06
     WebSocket
    0.06
    rud
    0.06
     MAIL
    0.06
    UEL
    0.06
    Act Density 0.005%

    No Known Activations