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

    Neuronpedia

    INDEX
    Explanations

    with or as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Creating
    0.14
     Setup
    0.14
     Device
    0.14
     Created
    0.13
     创建
    0.13
     identifies
    0.13
     achieves
    0.13
     Adap
    0.13
     created
    0.13
     发
    0.13
    POSITIVE LOGITS
     വിശദ
    0.16
     hindsight
    0.15
     penjelasan
    0.15
     vehement
    0.14
    ሙሉ
    0.14
     उनके
    0.14
     impunity
    0.14
     normalcy
    0.14
     cursory
    0.14
     معين
    0.14
    Act Density 0.105%

    No Known Activations