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

    Neuronpedia

    INDEX
    Explanations

    .length

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indefinitely
    -0.07
     minimized
    -0.07
    很快就
    -0.07
    Modify
    -0.07
     unavoid
    -0.07
    下去
    -0.07
     necklace
    -0.07
    daughter
    -0.07
     arsenal
    -0.07
    .quant
    -0.07
    POSITIVE LOGITS
    _fg
    0.08
    INVAL
    0.08
    общи
    0.07
    菅
    0.07
     Rohingya
    0.07
    乌鲁木
    0.07
    _ESCAPE
    0.07
    SPI
    0.07
    ��
    0.07
    ὄ
    0.07
    Act Density 0.005%

    No Known Activations