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

    Neuronpedia

    INDEX
    Explanations

    Permutations and arrangements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Delete
    -0.09
     Faux
    -0.09
    mins
    -0.08
     discourage
    -0.08
    ixin
    -0.08
     dissent
    -0.08
     بلا
    -0.07
    jö
    -0.07
    جا
    -0.07
     kink
    -0.07
    POSITIVE LOGITS
     opportunities
    0.11
     oportunidades
    0.10
    机会
    0.10
    寻找
    0.09
     adapta
    0.09
    Searching
    0.09
    尝
    0.08
     możliwości
    0.08
    Availability
    0.08
    找到
    0.08
    Act Density 0.040%

    No Known Activations