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

    Neuronpedia

    INDEX
    Explanations

    smells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vill
    -0.07
     militar
    -0.07
     microscopic
    -0.06
     Schneider
    -0.06
     deter
    -0.06
     trenches
    -0.06
    Probe
    -0.06
    iset
    -0.06
     accidental
    -0.06
    foo
    -0.06
    POSITIVE LOGITS
     unsubscribe
    0.07
    iego
    0.07
    issing
    0.06
    assignment
    0.06
    .hex
    0.06
    ]';↵
    0.06
    sak
    0.06
    ergisi
    0.06
     речі
    0.06
    予約
    0.06
    Act Density 0.006%

    No Known Activations