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

    Neuronpedia

    INDEX
    Explanations

    gaining an advantage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highlight
    -0.07
     Assumes
    -0.07
     affirm
    -0.07
    simple
    -0.06
    _weight
    -0.06
    xico
    -0.06
     virus
    -0.06
     Variables
    -0.06
     Inquiry
    -0.06
     antigen
    -0.06
    POSITIVE LOGITS
    marketing
    0.07
    inux
    0.07
     indign
    0.06
    -match
    0.06
    mist
    0.06
     electrom
    0.06
    InTheDocument
    0.06
    ักด
    0.06
     pil
    0.06
     utens
    0.06
    Act Density 0.126%

    No Known Activations