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

    Neuronpedia

    INDEX
    Explanations

    strange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فيه
    -0.07
    fter
    -0.07
    .tif
    -0.07
     Per
    -0.07
    Hack
    -0.07
     wrought
    -0.07
    .Actions
    -0.07
    心仪
    -0.07
     Hak
    -0.07
     serviceName
    -0.06
    POSITIVE LOGITS
    捏
    0.07
     sandy
    0.07
    散布
    0.07
     мая
    0.07
     وأضاف
    0.07
    鲍
    0.07
    <body
    0.07
    毪
    0.07
    钼
    0.07
    :])↵
    0.06
    Act Density 0.083%

    No Known Activations