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

    Neuronpedia

    INDEX
    Explanations

    comma followed by clarification or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     increased
    1.01
     gradient
    0.94
     ejaculation
    0.93
     olives
    0.93
     omitted
    0.92
    increased
    0.91
    stered
    0.91
     panini
    0.89
     chloroplast
    0.89
     darkening
    0.88
    POSITIVE LOGITS
     Craft
    0.95
     Inc
    0.95
     Reasonable
    0.93
     Bone
    0.92
     Famous
    0.90
     Family
    0.89
     Boy
    0.89
     Your
    0.87
     Toys
    0.87
     Efficient
    0.87
    Act Density 0.022%

    No Known Activations