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

    Neuronpedia

    INDEX
    Explanations

    stuck

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Men
    -0.07
     fruit
    -0.07
    Endpoint
    -0.06
     fram
    -0.06
    -'
    -0.06
    -room
    -0.06
    adiator
    -0.06
     edible
    -0.06
     рес
    -0.06
    (user
    -0.06
    POSITIVE LOGITS
     stuck
    0.09
     bookmarks
    0.07
    _branch
    0.07
     \
    0.06
     Neither
    0.06
     sticks
    0.06
    _PKG
    0.06
    _exist
    0.06
     muttered
    0.06
                            
↵
    0.06
    Act Density 0.009%

    No Known Activations