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

    Neuronpedia

    INDEX
    Explanations

    immune

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     round
    -0.92
     dietro
    -0.80
    Round
    -0.80
     behind
    -0.78
     Sociales
    -0.77
    曖昧さ回避
    -0.76
    ագրություններ
    -0.75
     ddelweddau
    -0.75
     otomatig
    -0.74
     Behind
    -0.74
    POSITIVE LOGITS
     status
    0.65
     sensitivity
    0.56
     ze
    0.53
     pro
    0.51
     construction
    0.50
    ↵↵
    0.49
     state
    0.49
     chinh
    0.48
     len
    0.48
    MigrationBuilder
    0.48
    Act Density 0.286%

    No Known Activations