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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .g
    -0.09
    足够的
    -0.08
     out
    -0.07
    燃料
    -0.07
    .gr
    -0.07
    𬒗
    -0.07
    不得不
    -0.07
    强烈
    -0.06
     Landscape
    -0.06
    .`
    -0.06
    POSITIVE LOGITS
     bons
    0.08
    \Helper
    0.08
    _PHP
    0.07
    /node
    0.07
    Clients
    0.07
    topics
    0.07
     испол
    0.07
    callbacks
    0.07
    古镇
    0.07
    	cache
    0.07
    Act Density 0.135%

    No Known Activations