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

    Neuronpedia

    INDEX
    Explanations

    stated, adopted, preferred, done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     randomly
    0.37
     randomization
    0.36
     बेसब्री
    0.36
     incap
    0.36
    izability
    0.35
     namespace
    0.35
     ---
    0.35
     progressively
    0.35
    能够在
    0.35
     naturalmente
    0.34
    POSITIVE LOGITS
     enacted
    0.68
     happening
    0.68
     pursued
    0.68
     practised
    0.66
     apparent
    0.65
    done
    0.64
     done
    0.64
     obeyed
    0.64
     occurring
    0.62
     abused
    0.61
    Act Density 0.148%

    No Known Activations