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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     streak
    -0.07
    Cla
    -0.06
    alker
    -0.06
     sqrt
    -0.06
    规范
    -0.06
    xiv
    -0.06
     snake
    -0.06
     hierarchy
    -0.06
    ↵
↵
↵
↵
    -0.06
     desar
    -0.06
    POSITIVE LOGITS
     Only
    0.07
     only
    0.07
     이
    0.07
     ONLY
    0.07
    Only
    0.07
    .JsonProperty
    0.07
    過
    0.07
    .Classes
    0.07
     FindObjectOfType
    0.07
    ча
    0.07
    Act Density 0.009%

    No Known Activations