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

    Neuronpedia

    INDEX
    Explanations

    developer tools and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     योर
    0.28
     \\
    0.28
    aretro
    0.27
     temperate
    0.27
    真正的
    0.26
    河北
    0.25
    britann
    0.25
    離開
    0.24
     methotrexate
    0.24
    jLabel
    0.24
    POSITIVE LOGITS
    ®
    0.45
    ®,
    0.44
    ™
    0.39
    ™,
    0.38
    ®.
    0.37
     CLI
    0.36
    MyAdmin
    0.36
     >=
    0.35
    自带
    0.34
    ™.
    0.33
    Act Density 0.226%

    No Known Activations