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

    Neuronpedia

    INDEX
    Explanations

    follows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entered
    -0.07
    into
    -0.06
     geben
    -0.06
    ushman
    -0.06
    стоя
    -0.06
    ARED
    -0.06
     Dynamic
    -0.06
    011
    -0.06
     příjem
    -0.06
     mentioned
    -0.06
    POSITIVE LOGITS
    (if
    0.06
    .Listen
    0.06
     actionTypes
    0.06
    CCC
    0.06
    (State
    0.06
    eventName
    0.06
    ={({
    0.06
    .Ap
    0.06
     ActionTypes
    0.06
     Dolphin
    0.06
    Act Density 0.016%

    No Known Activations