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

    Neuronpedia

    INDEX
    Explanations

    political negotiations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tits
    -0.07
     propaganda
    -0.07
     tutor
    -0.07
     דואר
    -0.07
    _DROP
    -0.07
    ervo
    -0.06
    .translatesAutoresizingMaskIntoConstraints
    -0.06
    /tags
    -0.06
    並不
    -0.06
     researching
    -0.06
    POSITIVE LOGITS
    #+#+
    0.08
    珠海
    0.08
    风尚
    0.07
     Российской
    0.07
    잊
    0.06
    _pe
    0.06
     bear
    0.06
     Par
    0.06
    ৡ
    0.06
    �
    0.06
    Act Density 0.014%

    No Known Activations