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

    Neuronpedia

    INDEX
    Explanations

    Code database interaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     võ
    -0.08
    🛫
    -0.07
     Ear
    -0.07
    冰箱
    -0.07
     addCriterion
    -0.07
     Kant
    -0.07
    香菇
    -0.07
    引越し
    -0.07
    引っ越し
    -0.07
     Hindus
    -0.07
    POSITIVE LOGITS
    ?=
    0.08
    ebin
    0.07
    _LABEL
    0.07
    ESSAGE
    0.07
     NEO
    0.07
    ilate
    0.07
     admitted
    0.07
    由
    0.07
    occo
    0.07
    'in
    0.07
    Act Density 0.002%

    No Known Activations