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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VERBOSE
    -0.07
     assertNull
    -0.07
     Marketable
    -0.07
    맆
    -0.06
    守护
    -0.06
    Transmission
    -0.06
    callable
    -0.06
    (proxy
    -0.06
    	assertFalse
    -0.06
    ategy
    -0.06
    POSITIVE LOGITS
     Nina
    0.08
    ady
    0.07
     word
    0.07
    有一定
    0.07
    就有
    0.07
     wn
    0.07
    加分
    0.07
    panel
    0.07
     allev
    0.07
     Lucky
    0.07
    Act Density 0.040%

    No Known Activations