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

    Neuronpedia

    INDEX
    Explanations

    inputs and including

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     track
    0.55
     slotted
    0.49
     cumulative
    0.46
     pristine
    0.46
     tracked
    0.46
     logged
    0.45
     වශ
    0.45
     Track
    0.44
     cascading
    0.44
     single
    0.43
    POSITIVE LOGITS
    including
    0.80
    су
    0.76
    antan
    0.74
    instagood
    0.71
    zarchiwizowane
    0.71
    .•
    0.71
    .–
    0.70
    ettet
    0.70
    .[[
    0.69
    inden
    0.68
    Act Density 0.631%

    No Known Activations