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

    Neuronpedia

    INDEX
    Explanations

    how to make or build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lockers
    1.20
     soliton
    1.14
    %%
    1.12
     critérios
    1.10
    %%%
    1.08
     soins
    1.06
    edown
    1.05
    開催
    1.05
     wheel
    1.03
     learnings
    1.03
    POSITIVE LOGITS
    و
    1.36
     Actor
    1.24
     actor
    1.20
     actriz
    1.16
    actor
    1.14
    ygons
    1.10
    いない
    1.10
     idea
    1.08
    j
    1.07
     ital
    1.07
    Act Density 0.004%

    No Known Activations