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

    Neuronpedia

    INDEX
    Explanations

    items followed by a dash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ....
    1.31
    ",
    1.24
     ...
    1.24
    '',
    1.16
    ..."
    1.16
    ',
    1.16
     ..."
    1.14
       
    1.13
    ....
    1.12
    ''
    1.11
    POSITIVE LOGITS
    –
    1.40
    .–
    1.39
    )–
    1.28
    ／
    1.26
    َّ
    1.12
    اً
    1.11
    ––
    1.10
     „
    1.09
     ‚
    1.08
    1.08
    Act Density 0.158%

    No Known Activations