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

    Neuronpedia

    INDEX
    Explanations

    initial planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     implemented
    0.47
     estren
    0.46
     implementation
    0.46
     instructions
    0.46
     invariance
    0.44
     implementations
    0.44
     manutenção
    0.43
     substitution
    0.41
     SATA
    0.41
    implemented
    0.41
    POSITIVE LOGITS
     planning
    1.17
    planning
    1.15
     Planning
    1.13
    Planning
    1.12
     perencanaan
    1.09
     feasibility
    1.00
    规划
    0.98
     Planung
    0.98
    規劃
    0.98
     PLANNING
    0.96
    Act Density 0.025%

    No Known Activations