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

    Neuronpedia

    INDEX
    Explanations

    add

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     видно
    -0.07
     throttle
    -0.07
    embro
    -0.06
     henne
    -0.06
    letion
    -0.06
    /container
    -0.06
     designated
    -0.06
    .launch
    -0.06
    920
    -0.06
     logout
    -0.06
    POSITIVE LOGITS
    vr
    0.07
    щее
    0.06
    ).</
    0.06
    .</
    0.06
     vyž
    0.06
    porn
    0.06
     QU
    0.06
     Af
    0.06
    	wx
    0.06
    _li
    0.06
    Act Density 0.032%

    No Known Activations