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

    Neuronpedia

    INDEX
    Explanations

    creating new items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    处理
    0.37
     leiden
    0.37
    oureux
    0.36
     במש
    0.36
    缓解
    0.35
     состояния
    0.35
    磨
    0.35
     amoureux
    0.34
     stains
    0.34
    景色
    0.34
    POSITIVE LOGITS
     Creation
    0.83
     CREATE
    0.81
    createNew
    0.80
    新規
    0.79
     Creating
    0.78
    Creating
    0.77
     crear
    0.77
     Create
    0.75
     creación
    0.75
    ICreate
    0.74
    Act Density 0.215%

    No Known Activations