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

    Neuronpedia

    INDEX
    Explanations

    time prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Conditions
    -0.07
     recalling
    -0.07
    �n
    -0.06
    mens
    -0.06
    pet
    -0.06
     recur
    -0.06
    weit
    -0.06
    Sequential
    -0.06
     intellectuals
    -0.06
     wo
    -0.06
    POSITIVE LOGITS
    _rewards
    0.07
     jihad
    0.07
    ixer
    0.06
     unanim
    0.06
     Triple
    0.06
     Thornton
    0.06
    oom
    0.06
     admon
    0.06
    _LENGTH
    0.06
     мист
    0.06
    Act Density 0.019%

    No Known Activations