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

    Neuronpedia

    INDEX
    Explanations

    aplic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    girl
    -0.08
    崤
    -0.07
    礼包
    -0.07
    拖延
    -0.07
    أمر
    -0.07
    涮
    -0.07
    lotte
    -0.07
    Vault
    -0.07
     replen
    -0.07
    特朗
    -0.07
    POSITIVE LOGITS
    有的玩家
    0.07
    .Sm
    0.07
     Mos
    0.07
    	save
    0.07
     Ship
    0.06
     projectile
    0.06
     Projectile
    0.06
    	GPIO
    0.06
     pada
    0.06
     Hopefully
    0.06
    Act Density 0.011%

    No Known Activations