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

    Neuronpedia

    INDEX
    Explanations

    Sec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    083
    -0.07
    Head
    -0.07
    д
    -0.06
     جو
    -0.06
     birbir
    -0.06
    ])**
    -0.06
     mount
    -0.06
    ceptor
    -0.06
     trace
    -0.06
     traces
    -0.06
    POSITIVE LOGITS
    ]";↵
    0.07
    	rb
    0.06
    eting
    0.06
    olik
    0.06
     치
    0.06
    ald
    0.06
    ]");↵
    0.06
    '"↵
    0.06
     strm
    0.06
    YL
    0.06
    Act Density 0.001%

    No Known Activations