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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icide
    -0.07
    ogle
    -0.07
     Hello
    -0.07
    terminate
    -0.06
    Directive
    -0.06
     mailbox
    -0.06
    IBC
    -0.06
     Americans
    -0.06
    <Block
    -0.06
    ouncy
    -0.06
    POSITIVE LOGITS
     คณะ
    0.07
    /Instruction
    0.06
     FG
    0.06
    CUR
    0.06
    주세요
    0.06
    Obviously
    0.06
     수상
    0.06
     TOP
    0.06
    layers
    0.06
    _attrib
    0.06
    Act Density 0.020%

    No Known Activations