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

    Neuronpedia

    INDEX
    Explanations

    here is the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    412
    -0.10
    squ
    -0.09
    Â
    -0.09
    rnek
    -0.09
     ifndef
    -0.09
    indi
    -0.09
    (çģ«
    -0.09
     Strom
    -0.09
    ayer
    -0.08
    veis
    -0.08
    POSITIVE LOGITS
    :\n
    0.15
    :\n\n
    0.12
    âĨĵ
    0.11
    ):\n
    0.11
    ä¾Ľ
    0.11
    ]:\n
    0.10
    :\n\n\n
    0.10
    ":\n
    0.10
     folks
    0.10
     followed
    0.10
    Act Density 0.235%

    No Known Activations