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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "},"
    -0.06
    ,Integer
    -0.06
     Shutdown
    -0.06
    ']},↵
    -0.06
    .ERR
    -0.06
     avg
    -0.06
    skému
    -0.06
    (Common
    -0.06
     homosexual
    -0.05
    ())),↵
    -0.05
    POSITIVE LOGITS
    uis
    0.09
    이다
    0.08
    hyp
    0.07
     to
    0.07
    かの
    0.07
    rip
    0.07
    ince
    0.07
    �
    0.07
     TO
    0.07
    -The
    0.06
    Act Density 0.493%

    No Known Activations