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

    Neuronpedia

    INDEX
    Explanations

    structured learning examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     policewomen
    0.37
     bibliographic
    0.35
     computational
    0.35
    as
    0.32
     vectorized
    0.31
    unnel
    0.31
    や
    0.31
    autoarima
    0.31
     and
    0.31
    permissionid
    0.31
    POSITIVE LOGITS
     Skills
    0.41
    Skills
    0.40
    Learning
    0.40
     umiejęt
    0.39
     Skill
    0.38
     Fähigkeiten
    0.38
    Your
    0.37
    Skill
    0.36
    告诉
    0.36
    表现
    0.35
    Act Density 0.002%

    No Known Activations