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

    Neuronpedia

    INDEX
    Explanations

    backtracking search algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anthocyan
    0.50
     capuche
    0.47
     loaves
    0.46
     anth
    0.45
    στι
    0.44
     purchases
    0.43
     meriye
    0.42
     compressor
    0.42
     malonyl
    0.42
     streamwise
    0.41
    POSITIVE LOGITS
     Solving
    0.57
     Giải
    0.54
     Fields
    0.52
     Pencil
    0.52
     Solve
    0.49
     Field
    0.48
     Healing
    0.48
     Restoration
    0.48
     Solver
    0.48
     Completion
    0.46
    Act Density 0.044%

    No Known Activations