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

    Neuronpedia

    INDEX
    Explanations

    sanctuary, retreat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مد
    -0.07
     kalk
    -0.07
    Number
    -0.07
     linear
    -0.07
     timelines
    -0.06
     модель
    -0.06
     đời
    -0.06
     ارد
    -0.06
    umbotron
    -0.06
     Alignment
    -0.06
    POSITIVE LOGITS
     sanctuary
    0.14
     refuge
    0.13
     haven
    0.11
     Sanctuary
    0.10
     retreat
    0.10
     Haven
    0.10
     Refuge
    0.09
     Citadel
    0.08
    сут
    0.08
     fortress
    0.08
    Act Density 0.008%

    No Known Activations