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

    Neuronpedia

    INDEX
    Explanations

    dependencies and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.61
    ik
    0.57
    r
    0.57
    чним
    0.54
    ia
    0.50
    ahili
    0.49
    anese
    0.48
    icata
    0.47
     упо
    0.45
    ikr
    0.45
    POSITIVE LOGITS
     dependencies
    0.53
     Dependencies
    0.50
     dependen
    0.50
     dependences
    0.49
     consequences
    0.48
     dependence
    0.48
     abhäng
    0.48
     bays
    0.46
     dependency
    0.45
    dependence
    0.45
    Act Density 0.004%

    No Known Activations