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

    Neuronpedia

    INDEX
    Explanations

    worsening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LU
    -0.07
    ustomed
    -0.07
    Aliases
    -0.07
     mel
    -0.06
     Kürt
    -0.06
     deber
    -0.06
    妮
    -0.06
    @
    -0.06
     humming
    -0.06
    Stuff
    -0.06
    POSITIVE LOGITS
    _DIST
    0.06
    ॰
    0.06
     متف
    0.06
    -прав
    0.06
     Surround
    0.06
    گه
    0.06
    _PERCENT
    0.06
    _SEL
    0.06
     xuất
    0.06
    awning
    0.06
    Act Density 0.057%

    No Known Activations