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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ontent
    -0.06
    ISODE
    -0.06
     Naturally
    -0.06
    olic
    -0.06
    eec
    -0.06
    Attachments
    -0.06
    及び
    -0.06
     Arrival
    -0.06
     consect
    -0.06
     cruis
    -0.06
    POSITIVE LOGITS
    .App
    0.07
     decision
    0.07
     رضا
    0.06
     archit
    0.06
     万元
    0.06
    	Vk
    0.06
    rgctx
    0.06
    relay
    0.06
     хотел
    0.06
     Decision
    0.06
    Act Density 0.026%

    No Known Activations