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

    Neuronpedia

    INDEX
    Explanations

    strains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .WinForms
    -0.07
    _male
    -0.06
    	router
    -0.06
    .set
    -0.06
     ville
    -0.06
    ۱۳۸
    -0.06
    729
    -0.06
    ۱۸
    -0.06
    .have
    -0.06
     VP
    -0.06
    POSITIVE LOGITS
    OMATIC
    0.07
     Loving
    0.06
     prepar
    0.06
     éc
    0.06
    容
    0.06
    ansas
    0.06
     effic
    0.06
    /item
    0.06
     coraz
    0.06
    uffer
    0.06
    Act Density 0.034%

    No Known Activations