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

    Neuronpedia

    INDEX
    Explanations

    Leaving notes/acts of kindness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ASN
    -0.08
    inflate
    -0.08
     dhal
    -0.08
     الدين
    -0.08
     suke
    -0.08
     inflation
    -0.08
     datatype
    -0.08
     printf
    -0.07
    Dialect
    -0.07
     importa
    -0.07
    POSITIVE LOGITS
     doorstep
    0.10
    窝
    0.10
     রেখে
    0.10
    留下
    0.09
     laissé
    0.09
    ไว้
    0.09
     छो
    0.09
     déposer
    0.09
     laiss
    0.09
     anonymously
    0.09
    Act Density 0.120%

    No Known Activations