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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wors
    -0.06
     sectarian
    -0.06
     preempt
    -0.06
    recommended
    -0.06
     Κο
    -0.06
     які
    -0.06
    MMMM
    -0.06
     cooperative
    -0.06
     complic
    -0.06
    _processors
    -0.06
    POSITIVE LOGITS
    _frm
    0.06
    (elements
    0.06
    ाकर
    0.06
    ışık
    0.06
    _Success
    0.06
    ΙΟ
    0.06
    워
    0.06
    _FILENAME
    0.06
    .setAlignment
    0.06
    فو
    0.06
    Act Density 0.100%

    No Known Activations