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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    计算器
    -0.06
     Okay
    -0.06
    mitter
    -0.06
     cmb
    -0.06
    firebase
    -0.06
    Marco
    -0.06
    ➰
    -0.06
    ﮃ
    -0.06
    ᐢ
    -0.06
    .zz
    -0.06
    POSITIVE LOGITS
     legal
    0.07
     danced
    0.07
     Direct
    0.07
    ventions
    0.07
    شار
    0.07
    ,dim
    0.07
     Hawks
    0.07
    reatest
    0.07
     conventions
    0.07
    _RELEASE
    0.07
    Act Density 0.002%

    No Known Activations