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

    Neuronpedia

    INDEX
    Explanations

    the word "another" followed by almost any other word

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    559
    -0.07
    umbing
    -0.06
    ÑĩиÑģл
    -0.06
    梨
    -0.06
    ajo
    -0.06
    ilar
    -0.06
    iram
    -0.06
    -enable
    -0.06
    asad
    -0.05
    ipse
    -0.05
    POSITIVE LOGITS
    adder
    0.07
    .epam
    0.06
    ê¶ģ
    0.06
    alone
    0.06
    $MESS
    0.06
     layer
    0.06
    891
    0.06
    -than
    0.06
    ίδ
    0.06
     aspect
    0.06
    Act Density 0.122%

    No Known Activations