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

    Neuronpedia

    INDEX
    Explanations

    neuron threshold condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aków
    0.43
    ഌ
    0.36
     Vj
    0.36
    पाठ
    0.35
    TabIndex
    0.35
     subcut
    0.35
    ULATION
    0.35
    俎
    0.35
    uania
    0.34
    kingdom
    0.34
    POSITIVE LOGITS
     Jimmy
    0.45
    Jimmy
    0.42
     dope
    0.40
     swing
    0.40
     Bann
    0.40
     leg
    0.39
     arm
    0.38
     bann
    0.38
     hook
    0.38
     loin
    0.38
    Act Density 0.001%

    No Known Activations