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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    から
    -0.07
    StorageSync
    -0.06
    .fig
    -0.06
     nostalg
    -0.06
    (flow
    -0.06
     Tower
    -0.06
    [msg
    -0.06
     </
    -0.05
     proactive
    -0.05
    под
    -0.05
    POSITIVE LOGITS
    .pc
    0.08
    ***
    0.07
     caso
    0.07
    自动
    0.07
    _children
    0.07
    eatures
    0.06
     Prepared
    0.06
     нек
    0.06
     Ancient
    0.06
     defStyle
    0.06
    Act Density 0.031%

    No Known Activations