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

    Neuronpedia

    INDEX
    Explanations

    ir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zion
    -0.07
    ıma
    -0.07
    erule
    -0.06
     daring
    -0.06
    DON
    -0.06
     Gian
    -0.06
    рій
    -0.06
    erken
    -0.06
     MIX
    -0.06
     trauma
    -0.06
    POSITIVE LOGITS
    veyor
    0.06
    icemail
    0.06
    nist
    0.06
    (sqrt
    0.06
     SSE
    0.06
    	ms
    0.05
    ilinear
    0.05
    在线视频
    0.05
    ActionTypes
    0.05
    enguins
    0.05
    Act Density 0.001%

    No Known Activations