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

    Neuronpedia

    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frække
    -0.06
     інформації
    -0.06
    될
    -0.06
    ">',↵
    -0.06
     Newark
    -0.06
     stderr
    -0.06
     Terminator
    -0.06
    _ch
    -0.06
     FIXME
    -0.06
    _objs
    -0.06
    POSITIVE LOGITS
    list
    0.08
    らず
    0.07
     consider
    0.07
    _once
    0.07
     nationalists
    0.07
     vinc
    0.06
    名稱
    0.06
     mocks
    0.06
    선
    0.06
     dissent
    0.06
    Act Density 0.005%

    No Known Activations