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

    Neuronpedia

    INDEX
    Explanations

    fun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dword
    -0.07
     Dispatcher
    -0.06
    yards
    -0.06
     massively
    -0.06
     Tiger
    -0.06
     jane
    -0.06
     trọng
    -0.06
     noises
    -0.06
     resembl
    -0.06
     Guardians
    -0.06
    POSITIVE LOGITS
     Fun
    0.08
    [Unit
    0.08
     softball
    0.07
    SupportedContent
    0.07
    �乐
    0.07
    บอล
    0.07
     cuenta
    0.07
    _icon
    0.06
    oba
    0.06
    uba
    0.06
    Act Density 0.014%

    No Known Activations