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

    Neuronpedia

    INDEX
    Explanations

    implied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wt
    -0.07
    -dess
    -0.06
    ».↵↵
    -0.06
     frightening
    -0.06
    .High
    -0.06
    技术
    -0.06
     EXT
    -0.06
    平方
    -0.06
    )b
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    گار
    0.07
    ưởng
    0.07
     yerinde
    0.06
    .atom
    0.06
     platinum
    0.06
     Registro
    0.06
    soup
    0.06
     overlooked
    0.06
     arranged
    0.06
    (Optional
    0.06
    Act Density 0.001%

    No Known Activations