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

    Neuronpedia

    INDEX
    Explanations

    safety and smallness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dropdown
    -0.07
    켜
    -0.06
    ові
    -0.06
     "")
↵
    -0.06
     chores
    -0.06
    /global
    -0.06
     farms
    -0.06
     chủ
    -0.06
     새
    -0.06
    -photo
    -0.06
    POSITIVE LOGITS
     unemployed
    0.07
     dek
    0.06
    'est
    0.06
    fell
    0.06
     Removes
    0.06
    .stride
    0.06
     wirk
    0.06
    ’est
    0.06
    singleton
    0.06
     air
    0.06
    Act Density 0.003%

    No Known Activations