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

    Neuronpedia

    INDEX
    Explanations

    pairs of things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     décisions
    -0.66
     compréhen
    -0.61
     préoccup
    -0.60
     acteur
    -0.60
    GraphicsUnit
    -0.60
     échanges
    -0.60
     vermelhas
    -0.59
     avoient
    -0.58
     BehaviorSubject
    -0.58
    SBATCH
    -0.57
    POSITIVE LOGITS
     among
    0.53
    DockStyle
    0.52
     مواليد
    0.45
     around
    0.42
    AxisAlignment
    0.40
     at
    0.40
    Finalize
    0.39
    ագրություններ
    0.39
     out
    0.38
    ínű
    0.38
    Act Density 0.002%

    No Known Activations