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

    Neuronpedia

    INDEX
    Explanations

    seeking professional help/therapy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    926
    -0.06
    _linux
    -0.06
    76
    -0.06
    .True
    -0.06
    UIBarButtonItem
    -0.06
    摸
    -0.06
    _hook
    -0.06
     motivate
    -0.06
    {}]
    -0.05
     strategic
    -0.05
    POSITIVE LOGITS
     wart
    0.08
     Mam
    0.07
    (encoded
    0.07
     mam
    0.06
     pf
    0.06
     Din
    0.06
     trest
    0.06
     установ
    0.06
    axios
    0.06
    _FL
    0.06
    Act Density 0.041%

    No Known Activations