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

    Neuronpedia

    INDEX
    Explanations

    middle aged managers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drivetrain
    0.35
     endpoints
    0.32
     interfacing
    0.32
     velocities
    0.32
     checkboxes
    0.32
     assistive
    0.32
     equilibration
    0.32
    𝘃
    0.30
     backend
    0.30
     structuring
    0.29
    POSITIVE LOGITS
    比特
    0.39
     connot
    0.31
     कठिना
    0.30
    破解
    0.29
    痛苦
    0.29
    美好的
    0.28
     awakened
    0.28
    0.28
    往往
    0.27
    consciously
    0.27
    Act Density 0.000%

    No Known Activations