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

    Neuronpedia

    INDEX
    Explanations

    Code installation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    总觉得
    -0.07
    PLE
    -0.07
    OLUM
    -0.07
    elm
    -0.06
    .PUT
    -0.06
     diffé
    -0.06
    考える
    -0.06
    aurant
    -0.06
    饭
    -0.06
    ADMIN
    -0.06
    POSITIVE LOGITS
     cruelty
    0.07
     morale
    0.07
    _g
    0.07
    eid
    0.07
    在美国
    0.06
     gob
    0.06
     SMA
    0.06
    	action
    0.06
     sho
    0.06
    acades
    0.06
    Act Density 0.040%

    No Known Activations