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

    Neuronpedia

    INDEX
    Explanations

    Scientific experiments with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Process
    -0.07
     results
    -0.07
     Doing
    -0.06
     chatting
    -0.06
     Super
    -0.06
     pain
    -0.06
     Mun
    -0.06
    .rect
    -0.06
     early
    -0.06
     вза
    -0.06
    POSITIVE LOGITS
     �
    0.07
    _tim
    0.07
    	on
    0.06
     उ
    0.06
    punkt
    0.06
    subscribe
    0.06
    ]['
    0.06
    dorf
    0.06
    /questions
    0.06
     refill
    0.06
    Act Density 0.066%

    No Known Activations