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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     استاد
    -0.07
     &,
    -0.06
    .Gr
    -0.06
    Failure
    -0.06
     Nikol
    -0.06
     μ
    -0.06
    Naz
    -0.06
     replic
    -0.06
     IPV
    -0.06
    ер
    -0.06
    POSITIVE LOGITS
    	friend
    0.07
     herald
    0.07
    /message
    0.07
     Simmons
    0.06
    addon
    0.06
    _SIZE
    0.06
    alf
    0.06
     Mercedes
    0.06
    _bed
    0.06
     اجازه
    0.06
    Act Density 0.144%

    No Known Activations