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

    Neuronpedia

    INDEX
    Explanations

    Encyclopedia references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Particip
    -0.07
     cooks
    -0.07
    掘
    -0.07
    .allocate
    -0.07
     COVID
    -0.07
     השק
    -0.07
    祝
    -0.06
     dept
    -0.06
     beg
    -0.06
     tecn
    -0.06
    POSITIVE LOGITS
    �
    0.08
    difficulty
    0.07
    imitives
    0.07
    ูล
    0.07
    持有的
    0.07
    cases
    0.07
    ansion
    0.07
    dic
    0.07
    áticas
    0.07
    ẅ
    0.07
    Act Density 0.033%

    No Known Activations