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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hindered
    -0.08
     По
    -0.07
    	H
    -0.07
     childish
    -0.07
    oidal
    -0.07
     콜
    -0.07
     Trail
    -0.06
    $("#
    -0.06
    .daily
    -0.06
     Tobacco
    -0.06
    POSITIVE LOGITS
     діяльність
    0.06
     unofficial
    0.06
    ?↵↵↵
    0.06
    ....↵↵
    0.06
     Took
    0.06
     ppl
    0.06
     slated
    0.06
    ?",
    0.06
    _expect
    0.05
     Shipping
    0.05
    Act Density 0.011%

    No Known Activations