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

    Neuronpedia

    INDEX
    Explanations

    writing prompts with constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.18
    uirre
    0.18
    How
    0.17
    directory
    0.17
    皆さん
    0.17
    What
    0.17
    team
    0.17
    <h3>
    0.17
    si
    0.17
    com
    0.17
    POSITIVE LOGITS
     vesicles
    0.22
     hydrolysis
    0.22
     moldings
    0.21
     hemoglobin
    0.21
     patties
    0.21
     ovarian
    0.20
     ovaries
    0.20
     chromosome
    0.19
     duplication
    0.19
     ovary
    0.19
    Act Density 0.005%

    No Known Activations