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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plex
    -0.07
    _Float
    -0.06
    eder
    -0.06
     Craigslist
    -0.06
     můj
    -0.06
     pruning
    -0.06
    charging
    -0.06
     Cup
    -0.06
    菜
    -0.06
    VID
    -0.06
    POSITIVE LOGITS
     capitalize
    0.07
    shm
    0.06
    称
    0.06
     Syntax
    0.06
    ainers
    0.06
     blind
    0.06
    _ARGS
    0.05
     Handbook
    0.05
     野
    0.05
     повинен
    0.05
    Act Density 0.000%

    No Known Activations