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

    Neuronpedia

    INDEX
    Explanations

    maximizing impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     postpone
    0.39
    rombin
    0.39
     variance
    0.38
     linearity
    0.38
     laid
    0.38
     reconcile
    0.38
    麿
    0.37
     Laid
    0.37
     mediate
    0.36
     Maze
    0.36
    POSITIVE LOGITS
    ल्लू
    0.44
    瑷
    0.42
    StateToProps
    0.40
    тив
    0.40
    ስቃሴ
    0.39
    InstanceManager
    0.38
    Effect
    0.38
     केश
    0.37
     нико
    0.36
     Johnson
    0.36
    Act Density 0.001%

    No Known Activations