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

    Neuronpedia

    INDEX
    Explanations

    construction/barriers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fluid
    -0.07
    filer
    -0.07
     taboo
    -0.07
    Stride
    -0.07
    =YES
    -0.07
     situations
    -0.07
     dựng
    -0.06
    "))↵
    -0.06
    맨
    -0.06
    _CI
    -0.06
    POSITIVE LOGITS
    othy
    0.06
     esse
    0.06
    §ظ
    0.06
    ties
    0.06
     نسخ
    0.06
    少し
    0.06
     causa
    0.06
     '!
    0.06
     somebody
    0.05
    CURRENT
    0.05
    Act Density 0.040%

    No Known Activations