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

    Neuronpedia

    INDEX
    Explanations

    core principles and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VENTION
    0.51
    IRONMENT
    0.50
    )$\
    0.47
    )।
    0.46
    )$.
    0.46
     antice
    0.45
     PCBs
    0.45
    老
    0.45
     S
    0.44
     mucous
    0.44
    POSITIVE LOGITS
    ist
    0.49
    entially
    0.45
    ium
    0.44
     presided
    0.43
     gespielt
    0.43
    istani
    0.43
     Balliye
    0.43
     complimented
    0.42
     engag
    0.41
    umni
    0.41
    Act Density 0.007%

    No Known Activations