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

    Neuronpedia

    INDEX
    Explanations

    code initialization and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    衅
    0.40
    btnAdd
    0.40
     één
    0.39
    addNew
    0.38
    мышлен
    0.36
    btnLogin
    0.36
    newItem
    0.36
    azor
    0.36
    น์โหลด
    0.36
     जान
    0.36
    POSITIVE LOGITS
     weights
    0.68
     candidates
    0.62
     temperatures
    0.60
    weights
    0.59
     colors
    0.58
     indices
    0.57
     allClasses
    0.57
     scores
    0.56
     pairs
    0.55
     trajectories
    0.55
    Act Density 0.043%

    No Known Activations